query
stringlengths 1.01k
96.3k
| response
stringlengths 16
25.2k
| rejected_response
stringlengths 16
106k
| source
stringclasses 9
values |
|---|---|---|---|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Rabinovich is winding up his term as ambassador .
|
<response><person>Rabinovich</person> is winding up his term as ambassador .</response>
|
{"entities": [{"text": "Rabinovich", "type": "person"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
He will be replaced by Eliahu Ben-Elissar , a former Israeli envoy to Egypt and right-wing Likud party politician .
|
<response>He will be replaced by <person>Eliahu Ben-Elissar</person> , a former <miscellaneous>Israeli</miscellaneous> envoy to <location>Egypt</location> and right-wing <organization>Likud</organization> party politician .</response>
|
{"entities": [{"text": "Eliahu Ben-Elissar", "type": "person"}, {"text": "Israeli", "type": "miscellaneous"}, {"text": "Egypt", "type": "location"}, {"text": "Likud", "type": "organization"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Israel on Wednesday sent Syria a message , via Washington , saying it was committed to peace and wanted to open negotiations without preconditions .
|
{"entities": [{"text": "Israel", "type": "location"}, {"text": "Syria", "type": "location"}, {"text": "Washington", "type": "location"}]}
|
<response><location>Israel</location> on Wednesday sent <location>Syria</location> a message , via <location>Washington</location> , saying it was committed to peace and wanted to open negotiations without preconditions .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
But it slammed Damascus for creating what it called a dangerous atmosphere .
|
{"entities": [{"text": "Damascus", "type": "location"}]}
|
<response>But it slammed <location>Damascus</location> for creating what it called a dangerous atmosphere .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Syria accused Israel on Wednesday of launching a hysterical campaign against it after Israeli television reported that Damascus had recently test fired a missile .
|
<response><location>Syria</location> accused <location>Israel</location> on Wednesday of launching a hysterical campaign against it after <miscellaneous>Israeli</miscellaneous> television reported that <location>Damascus</location> had recently test fired a missile .</response>
|
{"entities": [{"text": "Syria", "type": "location"}, {"text": "Israel", "type": "location"}, {"text": "Israeli", "type": "miscellaneous"}, {"text": "Damascus", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
It said its arms purchases were for defensive purposes .
|
{"entities": []}
|
<response>It said its arms purchases were for defensive purposes .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
" The message that we sent to ( Syrian President Hafez al- ) Assad is that Israel is ready at any time without preconditions to enter peace negotiations , " Israeli Foreign Minister David Levy told Israel Radio in an interview .
|
<response>" The message that we sent to ( <miscellaneous>Syrian</miscellaneous> President <person>Hafez al-</person> ) <person>Assad</person> is that <location>Israel</location> is ready at any time without preconditions to enter peace negotiations , " <miscellaneous>Israeli</miscellaneous> Foreign Minister <person>David Levy</person> told <organization>Israel Radio</organization> in an interview .</response>
|
{"entities": [{"text": "Syrian", "type": "miscellaneous"}, {"text": "Hafez al-", "type": "person"}, {"text": "Assad", "type": "person"}, {"text": "Israel", "type": "location"}, {"text": "Israeli", "type": "miscellaneous"}, {"text": "David Levy", "type": "person"}, {"text": "Israel Radio", "type": "organization"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Tension has mounted since Israeli Prime Minister Benjamin Netanyahu took office in June vowing to retain the Golan Heights Israel captured from Syria in the 1967 Middle East war .
|
{"entities": [{"text": "Israeli", "type": "miscellaneous"}, {"text": "Benjamin Netanyahu", "type": "person"}, {"text": "Golan Heights", "type": "location"}, {"text": "Israel", "type": "location"}, {"text": "Syria", "type": "location"}, {"text": "Middle East", "type": "location"}]}
|
<response>Tension has mounted since <miscellaneous>Israeli</miscellaneous> Prime Minister <person>Benjamin Netanyahu</person> took office in June vowing to retain the <location>Golan Heights</location> <location>Israel</location> captured from <location>Syria</location> in the 1967 <location>Middle East</location> war .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Israeli-Syrian peace talks have been deadlocked over the Golan since 1991 despite the previous government 's willingness to make Golan concessions .
|
<response><miscellaneous>Israeli-Syrian</miscellaneous> peace talks have been deadlocked over the <location>Golan</location> since 1991 despite the previous government 's willingness to make <location>Golan</location> concessions .</response>
|
{"entities": [{"text": "Israeli-Syrian", "type": "miscellaneous"}, {"text": "Golan", "type": "location"}, {"text": "Golan", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Peace talks between the two sides were last held in February .
|
{"entities": []}
|
<response>Peace talks between the two sides were last held in February .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
" The voices coming out of Damascus are bad , not good .
|
<response>" The voices coming out of <location>Damascus</location> are bad , not good .</response>
|
{"entities": [{"text": "Damascus", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
The media ...
|
{"entities": []}
|
<response>The media ...</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
are full of expressions and declarations that must be worrying ...
|
{"entities": []}
|
<response>are full of expressions and declarations that must be worrying ...</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
this artificial atmosphere is very dangerous because those who spread it could become its prisoners , " Levy said .
|
{"entities": [{"text": "Levy", "type": "person"}]}
|
<response>this artificial atmosphere is very dangerous because those who spread it could become its prisoners , " <person>Levy</person> said .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
" We expect from Syria , if its face is to peace , that it will answer Israel 's message to enter peace negotiations because that is our goal , " he said . "
|
<response>" We expect from <location>Syria</location> , if its face is to peace , that it will answer <location>Israel</location> 's message to enter peace negotiations because that is our goal , " he said . "</response>
|
{"entities": [{"text": "Syria", "type": "location"}, {"text": "Israel", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
We do not want a war , God forbid .
|
<response>We do not want a war , <person>God</person> forbid .</response>
|
{"entities": [{"text": "God", "type": "person"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
No one benefits from wars . "
|
<response>No one benefits from wars . "</response>
|
{"entities": []}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Israel 's Channel Two television said Damascus had sent a " calming signal " to Israel .
|
{"entities": [{"text": "Israel", "type": "location"}, {"text": "Channel Two", "type": "organization"}, {"text": "Damascus", "type": "location"}, {"text": "Israel", "type": "location"}]}
|
<response><location>Israel</location> 's <organization>Channel Two</organization> television said <location>Damascus</location> had sent a " calming signal " to <location>Israel</location> .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
It gave no source for the report .
|
{"entities": []}
|
<response>It gave no source for the report .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Netanyahu and Levy 's spokesmen said they could not confirm it .
|
<response><person>Netanyahu</person> and <person>Levy</person> 's spokesmen said they could not confirm it .</response>
|
{"entities": [{"text": "Netanyahu", "type": "person"}, {"text": "Levy", "type": "person"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
The television also said that Netanyahu had sent messages to reassure Syria via Cairo , the United States and Moscow .
|
{"entities": [{"text": "Netanyahu", "type": "person"}, {"text": "Syria", "type": "location"}, {"text": "Cairo", "type": "location"}, {"text": "United States", "type": "location"}, {"text": "Moscow", "type": "location"}]}
|
<response>The television also said that <person>Netanyahu</person> had sent messages to reassure <location>Syria</location> via <location>Cairo</location> , the <location>United States</location> and <location>Moscow</location> .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Polish diplomat denies nurses stranded in Libya .
|
<response><miscellaneous>Polish</miscellaneous> diplomat denies nurses stranded in <location>Libya</location> .</response>
|
{"entities": [{"text": "Polish", "type": "miscellaneous"}, {"text": "Libya", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
TUNIS 1996-08-22
|
{"entities": [{"text": "TUNIS", "type": "location"}]}
|
<response><location>TUNIS</location> 1996-08-22</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
A Polish diplomat on Thursday denied a Polish tabloid report this week that Libya was refusing exit visas to 100 Polish nurses trying to return home after working in the North African country .
|
<response>A <miscellaneous>Polish</miscellaneous> diplomat on Thursday denied a <miscellaneous>Polish</miscellaneous> tabloid report this week that <location>Libya</location> was refusing exit visas to 100 <miscellaneous>Polish</miscellaneous> nurses trying to return home after working in the <miscellaneous>North African</miscellaneous> country .</response>
|
{"entities": [{"text": "Polish", "type": "miscellaneous"}, {"text": "Polish", "type": "miscellaneous"}, {"text": "Libya", "type": "location"}, {"text": "Polish", "type": "miscellaneous"}, {"text": "North African", "type": "miscellaneous"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
" This is not true .
|
<response>" This is not true .</response>
|
{"entities": []}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Up to today , we have no knowledge of any nurse stranded or kept in Libya without her will , and we have not received any complaint , " the Polish embassy 's charge d'affaires in Tripoli , Tadeusz Awdankiewicz , told Reuters by telephone .
|
<response>Up to today , we have no knowledge of any nurse stranded or kept in <location>Libya</location> without her will , and we have not received any complaint , " the <miscellaneous>Polish</miscellaneous> embassy 's charge d'affaires in <location>Tripoli</location> , <person>Tadeusz Awdankiewicz</person> , told <organization>Reuters</organization> by telephone .</response>
|
{"entities": [{"text": "Libya", "type": "location"}, {"text": "Polish", "type": "miscellaneous"}, {"text": "Tripoli", "type": "location"}, {"text": "Tadeusz Awdankiewicz", "type": "person"}, {"text": "Reuters", "type": "organization"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Poland 's labour ministry said this week it would send a team to Libya to investigate , but Awdankiewicz said the probe was prompted by some nurses complaining about their work conditions such as non-payment of their salaries .
|
<response><location>Poland</location> 's labour ministry said this week it would send a team to <location>Libya</location> to investigate , but <person>Awdankiewicz</person> said the probe was prompted by some nurses complaining about their work conditions such as non-payment of their salaries .</response>
|
{"entities": [{"text": "Poland", "type": "location"}, {"text": "Libya", "type": "location"}, {"text": "Awdankiewicz", "type": "person"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
He said that there are an estimated 800 Polish nurses working in Libya .
|
{"entities": [{"text": "Polish", "type": "miscellaneous"}, {"text": "Libya", "type": "location"}]}
|
<response>He said that there are an estimated 800 <miscellaneous>Polish</miscellaneous> nurses working in <location>Libya</location> .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Two Iranian opposition leaders meet in Baghdad .
|
<response>Two <miscellaneous>Iranian</miscellaneous> opposition leaders meet in <location>Baghdad</location> .</response>
|
{"entities": [{"text": "Iranian", "type": "miscellaneous"}, {"text": "Baghdad", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Hassan Hafidh
|
{"entities": [{"text": "Hassan Hafidh", "type": "person"}]}
|
<response><person>Hassan Hafidh</person></response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
BAGHDAD 1996-08-22
|
{"entities": [{"text": "BAGHDAD", "type": "location"}]}
|
<response><location>BAGHDAD</location> 1996-08-22</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
An Iranian exile group based in Iraq vowed on Thursday to extend support to Iran 's Kurdish rebels after they were attacked by Iranian troops deep inside Iraq last month .
|
<response>An <miscellaneous>Iranian</miscellaneous> exile group based in <location>Iraq</location> vowed on Thursday to extend support to <location>Iran</location> 's <miscellaneous>Kurdish</miscellaneous> rebels after they were attacked by <miscellaneous>Iranian</miscellaneous> troops deep inside <location>Iraq</location> last month .</response>
|
{"entities": [{"text": "Iranian", "type": "miscellaneous"}, {"text": "Iraq", "type": "location"}, {"text": "Iran", "type": "location"}, {"text": "Kurdish", "type": "miscellaneous"}, {"text": "Iranian", "type": "miscellaneous"}, {"text": "Iraq", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
A Mujahideen Khalq statement said its leader Massoud Rajavi met in Baghdad the Secretary-General of the Kurdistan Democratic Party of Iran ( KDPI ) Hassan Rastegar on Wednesday and voiced his support to Iran 's rebel Kurds .
|
<response>A <organization>Mujahideen Khalq</organization> statement said its leader <person>Massoud Rajavi</person> met in <location>Baghdad</location> the Secretary-General of the <organization>Kurdistan Democratic Party of Iran</organization> ( <organization>KDPI</organization> ) <person>Hassan Rastegar</person> on Wednesday and voiced his support to <location>Iran</location> 's rebel <miscellaneous>Kurds</miscellaneous> .</response>
|
{"entities": [{"text": "Mujahideen Khalq", "type": "organization"}, {"text": "Massoud Rajavi", "type": "person"}, {"text": "Baghdad", "type": "location"}, {"text": "Kurdistan Democratic Party of Iran", "type": "organization"}, {"text": "KDPI", "type": "organization"}, {"text": "Hassan Rastegar", "type": "person"}, {"text": "Iran", "type": "location"}, {"text": "Kurds", "type": "miscellaneous"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
" Rajavi emphasised that the Iranian Resistance would continue to stand side by side with their Kurdish compatriots and the resistance movement in Iranian Kurdistan , " it said .
|
{"entities": [{"text": "Rajavi", "type": "miscellaneous"}, {"text": "Iranian", "type": "miscellaneous"}, {"text": "Resistance", "type": "organization"}, {"text": "Kurdish", "type": "miscellaneous"}, {"text": "Iranian Kurdistan", "type": "location"}]}
|
<response>" <miscellaneous>Rajavi</miscellaneous> emphasised that the <miscellaneous>Iranian</miscellaneous> <organization>Resistance</organization> would continue to stand side by side with their <miscellaneous>Kurdish</miscellaneous> compatriots and the resistance movement in <location>Iranian Kurdistan</location> , " it said .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
A spokesman for the group said the meeting " signals a new level of cooperation between Mujahideen Khalq and the Iranian Kurdish oppositions " .
|
<response>A spokesman for the group said the meeting " signals a new level of cooperation between <organization>Mujahideen Khalq</organization> and the <miscellaneous>Iranian Kurdish</miscellaneous> oppositions " .</response>
|
{"entities": [{"text": "Mujahideen Khalq", "type": "organization"}, {"text": "Iranian Kurdish", "type": "miscellaneous"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Iran heavily bombarded targets in northern Iraq in July in pursuit of KDPI guerrillas based in Iraqi Kurdish areas outside the control of the government in Baghdad .
|
{"entities": [{"text": "Iran", "type": "location"}, {"text": "Iraq", "type": "location"}, {"text": "KDPI", "type": "organization"}, {"text": "Iraqi Kurdish", "type": "miscellaneous"}, {"text": "Baghdad", "type": "location"}]}
|
<response><location>Iran</location> heavily bombarded targets in northern <location>Iraq</location> in July in pursuit of <organization>KDPI</organization> guerrillas based in <miscellaneous>Iraqi Kurdish</miscellaneous> areas outside the control of the government in <location>Baghdad</location> .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Iraqi Kurdish areas bordering Iran are under the control of guerrillas of the Iraqi Kurdish Patriotic Union of Kurdistan ( PUK ) group .
|
<response><miscellaneous>Iraqi Kurdish</miscellaneous> areas bordering <location>Iran</location> are under the control of guerrillas of the <organization>Iraqi Kurdish Patriotic Union of Kurdistan</organization> ( <organization>PUK</organization> ) group .</response>
|
{"entities": [{"text": "Iraqi Kurdish", "type": "miscellaneous"}, {"text": "Iran", "type": "location"}, {"text": "Iraqi Kurdish Patriotic Union of Kurdistan", "type": "organization"}, {"text": "PUK", "type": "organization"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
PUK and Iraq 's Kurdistan Democratic Party ( KDP ) the two main Iraqi Kurdish factions , have had northern Iraq under their control since Iraqi forces were ousted from Kuwait in the 1991 Gulf War .
|
{"entities": [{"text": "PUK", "type": "organization"}, {"text": "Iraq", "type": "location"}, {"text": "Kurdistan Democratic Party", "type": "organization"}, {"text": "KDP", "type": "organization"}, {"text": "Iraqi Kurdish", "type": "miscellaneous"}, {"text": "Iraq", "type": "location"}, {"text": "Iraqi", "type": "miscellaneous"}, {"text": "Kuwait", "type": "location"}, {"text": "Gulf War", "type": "miscellaneous"}]}
|
<response><organization>PUK</organization> and <location>Iraq</location> 's <organization>Kurdistan Democratic Party</organization> ( <organization>KDP</organization> ) the two main <miscellaneous>Iraqi Kurdish</miscellaneous> factions , have had northern <location>Iraq</location> under their control since <miscellaneous>Iraqi</miscellaneous> forces were ousted from <location>Kuwait</location> in the 1991 <miscellaneous>Gulf War</miscellaneous> .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Clashes between the two parties broke out at the weekend in the most serious fighting since a U.S.-sponsored ceasefire last year .
|
<response>Clashes between the two parties broke out at the weekend in the most serious fighting since a <miscellaneous>U.S.-sponsored</miscellaneous> ceasefire last year .</response>
|
{"entities": [{"text": "U.S.-sponsored", "type": "miscellaneous"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Mujahideen Khalq said Iranian troops had also been shelling KDP positions in Qasri region in Suleimaniya province near the Iranian border over the last two days .
|
{"entities": [{"text": "Mujahideen Khalq", "type": "organization"}, {"text": "Iranian", "type": "miscellaneous"}, {"text": "KDP", "type": "organization"}, {"text": "Qasri", "type": "location"}, {"text": "Suleimaniya", "type": "location"}, {"text": "Iranian", "type": "miscellaneous"}]}
|
<response><organization>Mujahideen Khalq</organization> said <miscellaneous>Iranian</miscellaneous> troops had also been shelling <organization>KDP</organization> positions in <location>Qasri</location> region in <location>Suleimaniya</location> province near the <miscellaneous>Iranian</miscellaneous> border over the last two days .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
It said about 100 Iraqi Kurds were killed or wounded in the attack .
|
<response>It said about 100 <miscellaneous>Iraqi Kurds</miscellaneous> were killed or wounded in the attack .</response>
|
{"entities": [{"text": "Iraqi Kurds", "type": "miscellaneous"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Both Iran and Turkey mount air and land strikes at targets in northern Iraq in pursuit of their own Kurdish rebels .
|
{"entities": [{"text": "Iran", "type": "location"}, {"text": "Turkey", "type": "location"}, {"text": "Iraq", "type": "location"}, {"text": "Kurdish", "type": "miscellaneous"}]}
|
<response>Both <location>Iran</location> and <location>Turkey</location> mount air and land strikes at targets in northern <location>Iraq</location> in pursuit of their own <miscellaneous>Kurdish</miscellaneous> rebels .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
A U.S.-led air force in southern Turkey protects Iraqi Kurds from possible attacks by Baghdad troops .
|
{"entities": [{"text": "U.S.-led", "type": "miscellaneous"}, {"text": "Turkey", "type": "location"}, {"text": "Iraqi Kurds", "type": "miscellaneous"}, {"text": "Baghdad", "type": "location"}]}
|
<response>A <miscellaneous>U.S.-led</miscellaneous> air force in southern <location>Turkey</location> protects <miscellaneous>Iraqi Kurds</miscellaneous> from possible attacks by <location>Baghdad</location> troops .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Saudi riyal rates steady in quiet summer trade .
|
{"entities": [{"text": "Saudi", "type": "miscellaneous"}]}
|
<response><miscellaneous>Saudi</miscellaneous> riyal rates steady in quiet summer trade .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
MANAMA 1996-08-22
|
<response><location>MANAMA</location> 1996-08-22</response>
|
{"entities": [{"text": "MANAMA", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
The spot Saudi riyal against the dollar and riyal interbank deposit rates were mainly steady this week in quiet summer trade , dealers in the kingdom said .
|
{"entities": [{"text": "Saudi", "type": "miscellaneous"}]}
|
<response>The spot <miscellaneous>Saudi</miscellaneous> riyal against the dollar and riyal interbank deposit rates were mainly steady this week in quiet summer trade , dealers in the kingdom said .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
" There were no changes in Saudi riyal rates .
|
{"entities": [{"text": "Saudi", "type": "miscellaneous"}]}
|
<response>" There were no changes in <miscellaneous>Saudi</miscellaneous> riyal rates .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
The market was very quiet because of summer holidays , " one dealer said .
|
<response>The market was very quiet because of summer holidays , " one dealer said .</response>
|
{"entities": []}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
The spot riyal was put at 3.7504 / 06 to the dollar .
|
{"entities": []}
|
<response>The spot riyal was put at 3.7504 / 06 to the dollar .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
One-month interbank deposits were at 5-1/2 , 3/8 percent , three months were 5-5/8 , 1/2 percent and six months were 5-3/4 , 5/8 percent .
|
{"entities": [{"text": "One-month", "type": "miscellaneous"}]}
|
<response><miscellaneous>One-month</miscellaneous> interbank deposits were at 5-1/2 , 3/8 percent , three months were 5-5/8 , 1/2 percent and six months were 5-3/4 , 5/8 percent .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
One-year funds were at six , 5-7/8 percent .
|
<response><miscellaneous>One-year</miscellaneous> funds were at six , 5-7/8 percent .</response>
|
{"entities": [{"text": "One-year", "type": "miscellaneous"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Israel approves Arafat 's flight to West Bank .
|
{"entities": [{"text": "Israel", "type": "location"}, {"text": "Arafat", "type": "person"}, {"text": "West Bank", "type": "location"}]}
|
<response><location>Israel</location> approves <person>Arafat</person> 's flight to <location>West Bank</location> .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
JERUSALEM 1996-08-22
|
{"entities": [{"text": "JERUSALEM", "type": "location"}]}
|
<response><location>JERUSALEM</location> 1996-08-22</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Israel gave Palestinian President Yasser Arafat permission on Thursday to fly over its territory to the West Bank , ending a brief Israeli-PLO crisis , an Arafat adviser said .
|
{"entities": [{"text": "Israel", "type": "location"}, {"text": "Palestinian", "type": "miscellaneous"}, {"text": "Yasser Arafat", "type": "person"}, {"text": "West Bank", "type": "location"}, {"text": "Israeli-PLO", "type": "miscellaneous"}, {"text": "Arafat", "type": "person"}]}
|
<response><location>Israel</location> gave <miscellaneous>Palestinian</miscellaneous> President <person>Yasser Arafat</person> permission on Thursday to fly over its territory to the <location>West Bank</location> , ending a brief <miscellaneous>Israeli-PLO</miscellaneous> crisis , an <person>Arafat</person> adviser said .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
" The problem is over .
|
<response>" The problem is over .</response>
|
{"entities": []}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
The president 's aircraft has received permission to pass through Israeli airspace but the president is not expected to travel to the West Bank before Monday , " Nabil Abu Rdainah told Reuters .
|
<response>The president 's aircraft has received permission to pass through <miscellaneous>Israeli</miscellaneous> airspace but the president is not expected to travel to the <location>West Bank</location> before Monday , " <person>Nabil Abu Rdainah</person> told <organization>Reuters</organization> .</response>
|
{"entities": [{"text": "Israeli", "type": "miscellaneous"}, {"text": "West Bank", "type": "location"}, {"text": "Nabil Abu Rdainah", "type": "person"}, {"text": "Reuters", "type": "organization"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Arafat had been scheduled to meet former Israeli prime minister Shimon Peres in the West Bank town of Ramallah on Thursday but the venue was changed to Gaza after Israel denied flight clearance to the Palestinian leader 's helicopters .
|
<response><person>Arafat</person> had been scheduled to meet former <miscellaneous>Israeli</miscellaneous> prime minister <person>Shimon Peres</person> in the <location>West Bank</location> town of <location>Ramallah</location> on Thursday but the venue was changed to <location>Gaza</location> after <location>Israel</location> denied flight clearance to the <miscellaneous>Palestinian</miscellaneous> leader 's helicopters .</response>
|
{"entities": [{"text": "Arafat", "type": "person"}, {"text": "Israeli", "type": "miscellaneous"}, {"text": "Shimon Peres", "type": "person"}, {"text": "West Bank", "type": "location"}, {"text": "Ramallah", "type": "location"}, {"text": "Gaza", "type": "location"}, {"text": "Israel", "type": "location"}, {"text": "Palestinian", "type": "miscellaneous"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Palestinian officials accused right-wing Prime Minister Benjamin Netanyahu of trying to stop the Ramallah meeting by keeping Arafat grounded .
|
{"entities": [{"text": "Palestinian", "type": "miscellaneous"}, {"text": "Benjamin Netanyahu", "type": "person"}, {"text": "Ramallah", "type": "location"}, {"text": "Arafat", "type": "person"}]}
|
<response><miscellaneous>Palestinian</miscellaneous> officials accused right-wing Prime Minister <person>Benjamin Netanyahu</person> of trying to stop the <location>Ramallah</location> meeting by keeping <person>Arafat</person> grounded .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Arafat subsequently cancelled a meeting between Israeli and PLO officials , on civilian affairs , at the Allenby Bridge crossing between Jordan and the West Bank .
|
{"entities": [{"text": "Arafat", "type": "person"}, {"text": "Israeli", "type": "miscellaneous"}, {"text": "PLO", "type": "organization"}, {"text": "Allenby Bridge", "type": "location"}, {"text": "Jordan", "type": "location"}, {"text": "West Bank", "type": "location"}]}
|
<response><person>Arafat</person> subsequently cancelled a meeting between <miscellaneous>Israeli</miscellaneous> and <organization>PLO</organization> officials , on civilian affairs , at the <location>Allenby Bridge</location> crossing between <location>Jordan</location> and the <location>West Bank</location> .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Abu Rdainah said Arafat had decided against flying to the West Bank on Thursday , after Israel lifted the ban , because he had a busy schedule in Gaza and would not be free until Monday .
|
<response><person>Abu Rdainah</person> said <person>Arafat</person> had decided against flying to the <location>West Bank</location> on Thursday , after <location>Israel</location> lifted the ban , because he had a busy schedule in <location>Gaza</location> and would not be free until Monday .</response>
|
{"entities": [{"text": "Abu Rdainah", "type": "person"}, {"text": "Arafat", "type": "person"}, {"text": "West Bank", "type": "location"}, {"text": "Israel", "type": "location"}, {"text": "Gaza", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Arafat to meet Peres in Gaza after flight ban .
|
<response><person>Arafat</person> to meet <person>Peres</person> in <location>Gaza</location> after flight ban .</response>
|
{"entities": [{"text": "Arafat", "type": "person"}, {"text": "Peres", "type": "person"}, {"text": "Gaza", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
JERUSALEM 1996-08-22
|
<response><location>JERUSALEM</location> 1996-08-22</response>
|
{"entities": [{"text": "JERUSALEM", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Yasser Arafat will meet Shimon Peres in Gaza on Thursday after Palestinians said the right-wing Israeli government had barred the Palestinian leader from flying to the West Bank for talks with the former prime minister .
|
{"entities": [{"text": "Yasser Arafat", "type": "person"}, {"text": "Shimon Peres", "type": "person"}, {"text": "Gaza", "type": "location"}, {"text": "Palestinians", "type": "miscellaneous"}, {"text": "Israeli", "type": "miscellaneous"}, {"text": "Palestinian", "type": "miscellaneous"}, {"text": "West Bank", "type": "location"}]}
|
<response><person>Yasser Arafat</person> will meet <person>Shimon Peres</person> in <location>Gaza</location> on Thursday after <miscellaneous>Palestinians</miscellaneous> said the right-wing <miscellaneous>Israeli</miscellaneous> government had barred the <miscellaneous>Palestinian</miscellaneous> leader from flying to the <location>West Bank</location> for talks with the former prime minister .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
" The meeting between Peres and Arafat will take place at Erez checkpoint in Gaza and not in Ramallah as planned , " Peres ' office said .
|
{"entities": [{"text": "Peres", "type": "person"}, {"text": "Arafat", "type": "person"}, {"text": "Erez", "type": "location"}, {"text": "Gaza", "type": "location"}, {"text": "Ramallah", "type": "location"}, {"text": "Peres", "type": "person"}]}
|
<response>" The meeting between <person>Peres</person> and <person>Arafat</person> will take place at <location>Erez</location> checkpoint in <location>Gaza</location> and not in <location>Ramallah</location> as planned , " <person>Peres</person> ' office said .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Palestinian officials said the Israeli government had barred Arafat from overflying Israel in a Palestinian helicopter to the West Bank in an attempt to bar the meeting with Peres .
|
{"entities": [{"text": "Palestinian", "type": "miscellaneous"}, {"text": "Israeli", "type": "miscellaneous"}, {"text": "Arafat", "type": "person"}, {"text": "Israel", "type": "location"}, {"text": "Palestinian", "type": "miscellaneous"}, {"text": "West Bank", "type": "location"}, {"text": "Peres", "type": "person"}]}
|
<response><miscellaneous>Palestinian</miscellaneous> officials said the <miscellaneous>Israeli</miscellaneous> government had barred <person>Arafat</person> from overflying <location>Israel</location> in a <miscellaneous>Palestinian</miscellaneous> helicopter to the <location>West Bank</location> in an attempt to bar the meeting with <person>Peres</person> .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Israeli Prime Minister Benjamin Netanyahu has accused opposition leader Peres , who he defeated in May elections , of trying to undermine his Likud government 's authority to conduct peace talks .
|
<response><miscellaneous>Israeli</miscellaneous> Prime Minister <person>Benjamin Netanyahu</person> has accused opposition leader <person>Peres</person> , who he defeated in May elections , of trying to undermine his <organization>Likud</organization> government 's authority to conduct peace talks .</response>
|
{"entities": [{"text": "Israeli", "type": "miscellaneous"}, {"text": "Benjamin Netanyahu", "type": "person"}, {"text": "Peres", "type": "person"}, {"text": "Likud", "type": "organization"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Afghan UAE embassy says Taleban guards going home .
|
<response><miscellaneous>Afghan</miscellaneous> <location>UAE</location> embassy says <miscellaneous>Taleban</miscellaneous> guards going home .</response>
|
{"entities": [{"text": "Afghan", "type": "miscellaneous"}, {"text": "UAE", "type": "location"}, {"text": "Taleban", "type": "miscellaneous"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Hilary Gush
|
<response><person>Hilary Gush</person></response>
|
{"entities": [{"text": "Hilary Gush", "type": "person"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
DUBAI 1996-08-22
|
<response><location>DUBAI</location> 1996-08-22</response>
|
{"entities": [{"text": "DUBAI", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Three Afghan guards brought to the United Arab Emirates last week by Russian hostages who escaped from the Taleban militia will return to Afghanistan in a few days , the Afghan embassy in Abu Dhabi said on Thursday .
|
<response>Three <miscellaneous>Afghan</miscellaneous> guards brought to the <location>United Arab Emirates</location> last week by <miscellaneous>Russian</miscellaneous> hostages who escaped from the <miscellaneous>Taleban</miscellaneous> militia will return to <location>Afghanistan</location> in a few days , the <miscellaneous>Afghan</miscellaneous> embassy in <location>Abu Dhabi</location> said on Thursday .</response>
|
{"entities": [{"text": "Afghan", "type": "miscellaneous"}, {"text": "United Arab Emirates", "type": "location"}, {"text": "Russian", "type": "miscellaneous"}, {"text": "Taleban", "type": "miscellaneous"}, {"text": "Afghanistan", "type": "location"}, {"text": "Afghan", "type": "miscellaneous"}, {"text": "Abu Dhabi", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
" Our ambassador is in touch with the UAE foreign ministry .
|
<response>" Our ambassador is in touch with the <location>UAE</location> foreign ministry .</response>
|
{"entities": [{"text": "UAE", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Their return to Afghanistan will take place in two or three days , " an embassy official said .
|
{"entities": [{"text": "Afghanistan", "type": "location"}]}
|
<response>Their return to <location>Afghanistan</location> will take place in two or three days , " an embassy official said .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
" The embassy is issuing them travel documents for their return to their homeland .
|
{"entities": []}
|
<response>" The embassy is issuing them travel documents for their return to their homeland .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
There is no objection to their travel , " he added .
|
{"entities": []}
|
<response>There is no objection to their travel , " he added .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
The three Islamic Taleban guards were overpowered by seven Russian aircrew who escaped to UAE state Sharjah last Friday on board their own aircraft after a year in the captivity of Taleban militia in Kandahar in southern Afghanistan .
|
<response>The three <miscellaneous>Islamic Taleban</miscellaneous> guards were overpowered by seven <miscellaneous>Russian</miscellaneous> aircrew who escaped to <location>UAE</location> state <location>Sharjah</location> last Friday on board their own aircraft after a year in the captivity of <miscellaneous>Taleban</miscellaneous> militia in <location>Kandahar</location> in southern <location>Afghanistan</location> .</response>
|
{"entities": [{"text": "Islamic Taleban", "type": "miscellaneous"}, {"text": "Russian", "type": "miscellaneous"}, {"text": "UAE", "type": "location"}, {"text": "Sharjah", "type": "location"}, {"text": "Taleban", "type": "miscellaneous"}, {"text": "Kandahar", "type": "location"}, {"text": "Afghanistan", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
The UAE said on Monday it would hand over the three to the International Red Crescent , possibly last Tuesday .
|
{"entities": [{"text": "UAE", "type": "location"}, {"text": "International Red Crescent", "type": "organization"}]}
|
<response>The <location>UAE</location> said on Monday it would hand over the three to the <organization>International Red Crescent</organization> , possibly last Tuesday .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
It has since been silent on the issue .
|
<response>It has since been silent on the issue .</response>
|
{"entities": []}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
When asked whether the three guards would travel back to Kandahar or the Afghan capital Kabul , the embassy official said : " That has not been decided , but possibly Kandahar . "
|
{"entities": [{"text": "Kandahar", "type": "location"}, {"text": "Afghan", "type": "miscellaneous"}, {"text": "Kabul", "type": "location"}, {"text": "Kandahar", "type": "location"}]}
|
<response>When asked whether the three guards would travel back to <location>Kandahar</location> or the <miscellaneous>Afghan</miscellaneous> capital <location>Kabul</location> , the embassy official said : " That has not been decided , but possibly <location>Kandahar</location> . "</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Kandahar is the headquarters of the opposition Taleban militia .
|
{"entities": [{"text": "Kandahar", "type": "location"}, {"text": "Taleban", "type": "miscellaneous"}]}
|
<response><location>Kandahar</location> is the headquarters of the opposition <miscellaneous>Taleban</miscellaneous> militia .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Kabul is controlled by President Burhanuddin Rabbani 's government , which Taleban is fighting to overthrow .
|
<response><location>Kabul</location> is controlled by President <person>Burhanuddin Rabbani</person> 's government , which <miscellaneous>Taleban</miscellaneous> is fighting to overthrow .</response>
|
{"entities": [{"text": "Kabul", "type": "location"}, {"text": "Burhanuddin Rabbani", "type": "person"}, {"text": "Taleban", "type": "miscellaneous"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
The embassy official said the three men , believed to be in their 20s , were currently in Abu Dhabi .
|
<response>The embassy official said the three men , believed to be in their 20s , were currently in <location>Abu Dhabi</location> .</response>
|
{"entities": [{"text": "Abu Dhabi", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
He did not elaborate .
|
{"entities": []}
|
<response>He did not elaborate .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
The Russians , working for the Aerostan firm in the Russian republic of Tatarstan , were taken hostage after a Taleban MiG-19 fighter forced their cargo plane to land in August 1995 .
|
<response>The <miscellaneous>Russians</miscellaneous> , working for the <organization>Aerostan</organization> firm in the <miscellaneous>Russian</miscellaneous> republic of <location>Tatarstan</location> , were taken hostage after a <miscellaneous>Taleban</miscellaneous> <miscellaneous>MiG-19</miscellaneous> fighter forced their cargo plane to land in August 1995 .</response>
|
{"entities": [{"text": "Russians", "type": "miscellaneous"}, {"text": "Aerostan", "type": "organization"}, {"text": "Russian", "type": "miscellaneous"}, {"text": "Tatarstan", "type": "location"}, {"text": "Taleban", "type": "miscellaneous"}, {"text": "MiG-19", "type": "miscellaneous"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Taleban said its shipment of ammunition from Albania was evidence of Russian military support for Rabbani 's government .
|
<response><miscellaneous>Taleban</miscellaneous> said its shipment of ammunition from <location>Albania</location> was evidence of <miscellaneous>Russian</miscellaneous> military support for <person>Rabbani</person> 's government .</response>
|
{"entities": [{"text": "Taleban", "type": "miscellaneous"}, {"text": "Albania", "type": "location"}, {"text": "Russian", "type": "miscellaneous"}, {"text": "Rabbani", "type": "person"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Moscow said the crew 's nationality was coincidental .
|
<response><location>Moscow</location> said the crew 's nationality was coincidental .</response>
|
{"entities": [{"text": "Moscow", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Numerous diplomatic attempts to free the seven failed .
|
<response>Numerous diplomatic attempts to free the seven failed .</response>
|
{"entities": []}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
The Russians , who said they overpowered the guards -- two armed with Kalashnikov automatic rifles -- while doing regular maintenance work on their Ilyushin 76 cargo plane last Friday , left the UAE capital Abu Dhabi for home on Sunday .
|
{"entities": [{"text": "Russians", "type": "miscellaneous"}, {"text": "Kalashnikov", "type": "miscellaneous"}, {"text": "Ilyushin 76", "type": "miscellaneous"}, {"text": "UAE", "type": "location"}, {"text": "Abu Dhabi", "type": "location"}]}
|
<response>The <miscellaneous>Russians</miscellaneous> , who said they overpowered the guards -- two armed with <miscellaneous>Kalashnikov</miscellaneous> automatic rifles -- while doing regular maintenance work on their <miscellaneous>Ilyushin 76</miscellaneous> cargo plane last Friday , left the <location>UAE</location> capital <location>Abu Dhabi</location> for home on Sunday .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Iraq 's Saddam meets Russia 's Zhirinovsky .
|
<response><location>Iraq</location> 's <person>Saddam</person> meets <location>Russia</location> 's <person>Zhirinovsky</person> .</response>
|
{"entities": [{"text": "Iraq", "type": "location"}, {"text": "Saddam", "type": "person"}, {"text": "Russia", "type": "location"}, {"text": "Zhirinovsky", "type": "person"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
BAGHDAD 1996-08-22
|
{"entities": [{"text": "BAGHDAD", "type": "location"}]}
|
<response><location>BAGHDAD</location> 1996-08-22</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Iraqi President Saddam Hussein has told visiting Russian ultra-nationalist Vladimir Zhirinovsky that Baghdad wanted to maintain " friendship and cooperation " with Moscow , official Iraqi newspapers said on Thursday .
|
{"entities": [{"text": "Iraqi", "type": "miscellaneous"}, {"text": "Saddam Hussein", "type": "person"}, {"text": "Russian", "type": "miscellaneous"}, {"text": "Vladimir Zhirinovsky", "type": "person"}, {"text": "Baghdad", "type": "location"}, {"text": "Moscow", "type": "location"}, {"text": "Iraqi", "type": "miscellaneous"}]}
|
<response><miscellaneous>Iraqi</miscellaneous> President <person>Saddam Hussein</person> has told visiting <miscellaneous>Russian</miscellaneous> ultra-nationalist <person>Vladimir Zhirinovsky</person> that <location>Baghdad</location> wanted to maintain " friendship and cooperation " with <location>Moscow</location> , official <miscellaneous>Iraqi</miscellaneous> newspapers said on Thursday .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
" President Saddam Hussein stressed during the meeting Iraq 's keenness to maintain friendship and cooperation with Russia , " the papers said .
|
<response>" President <person>Saddam Hussein</person> stressed during the meeting <location>Iraq</location> 's keenness to maintain friendship and cooperation with <location>Russia</location> , " the papers said .</response>
|
{"entities": [{"text": "Saddam Hussein", "type": "person"}, {"text": "Iraq", "type": "location"}, {"text": "Russia", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
They said Zhirinovsky told Saddam before he left Baghdad on Wednesday that his Liberal Democratic party and the Russian Duma ( parliament ) " are calling for an immediate lifting of the embargo " imposed on Iraq after its 1990 invasion of Kuwait .
|
{"entities": [{"text": "Zhirinovsky", "type": "person"}, {"text": "Saddam", "type": "person"}, {"text": "Baghdad", "type": "location"}, {"text": "Liberal Democratic party", "type": "organization"}, {"text": "Russian", "type": "miscellaneous"}, {"text": "Duma", "type": "organization"}, {"text": "Iraq", "type": "location"}, {"text": "Kuwait", "type": "location"}]}
|
<response>They said <person>Zhirinovsky</person> told <person>Saddam</person> before he left <location>Baghdad</location> on Wednesday that his <organization>Liberal Democratic party</organization> and the <miscellaneous>Russian</miscellaneous> <organization>Duma</organization> ( parliament ) " are calling for an immediate lifting of the embargo " imposed on <location>Iraq</location> after its 1990 invasion of <location>Kuwait</location> .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Zhirinovsky said on Tuesday he would press the Russian government to help end U.N. trade sanctions on Iraq and blamed Moscow for delaying establishment of good ties with Baghdad .
|
{"entities": [{"text": "Zhirinovsky", "type": "person"}, {"text": "Russian", "type": "miscellaneous"}, {"text": "U.N.", "type": "organization"}, {"text": "Iraq", "type": "location"}, {"text": "Moscow", "type": "location"}, {"text": "Baghdad", "type": "location"}]}
|
<response><person>Zhirinovsky</person> said on Tuesday he would press the <miscellaneous>Russian</miscellaneous> government to help end <organization>U.N.</organization> trade sanctions on <location>Iraq</location> and blamed <location>Moscow</location> for delaying establishment of good ties with <location>Baghdad</location> .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
" Our stand is firm , namely we are calling on ( the Russian ) government to end the economic embargo on Iraq and resume trade ties between Russia and Iraq , " he told reporters .
|
{"entities": [{"text": "Russian", "type": "miscellaneous"}, {"text": "Iraq", "type": "location"}, {"text": "Russia", "type": "location"}, {"text": "Iraq", "type": "location"}]}
|
<response>" Our stand is firm , namely we are calling on ( the <miscellaneous>Russian</miscellaneous> ) government to end the economic embargo on <location>Iraq</location> and resume trade ties between <location>Russia</location> and <location>Iraq</location> , " he told reporters .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
Zhirinovsky visited Iraq twice in 1995 .
|
{"entities": [{"text": "Zhirinovsky", "type": "person"}, {"text": "Iraq", "type": "location"}]}
|
<response><person>Zhirinovsky</person> visited <location>Iraq</location> twice in 1995 .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Last October he was invited to attend the referendum held on Iraq 's presidency , which extended Saddam 's term for seven more years .
|
<response>Last October he was invited to attend the referendum held on <location>Iraq</location> 's presidency , which extended <person>Saddam</person> 's term for seven more years .</response>
|
{"entities": [{"text": "Iraq", "type": "location"}, {"text": "Saddam", "type": "person"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
PRESS DIGEST - Iraq - Aug 22 .
|
{"entities": [{"text": "Iraq", "type": "location"}]}
|
<response>PRESS DIGEST - <location>Iraq</location> - Aug 22 .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
BAGHDAD 1996-08-22
|
<response><location>BAGHDAD</location> 1996-08-22</response>
|
{"entities": [{"text": "BAGHDAD", "type": "location"}]}
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and identify all named entities in JSON format.
For example:
Text: "John Smith works at Google in Mountain View."
JSON output:
{
"entities": [
{"text": "John Smith", "type": "person"},
{"text": "Google", "type": "organization"},
{"text": "Mountain View", "type": "location"}
]
}
Available entity types: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Return the entities in valid JSON format as shown in the example.
2. Include ALL entities you can identify with their exact text and type.
3. Do not include explanations, just the JSON object.
4. If entity spans overlap, choose the most specific entity type.
5. Ensure the JSON is properly formatted and valid.
Text to process:
These are some of the leading stories in the official Iraqi press on Thursday .
|
{"entities": [{"text": "Iraqi", "type": "miscellaneous"}]}
|
<response>These are some of the leading stories in the official <miscellaneous>Iraqi</miscellaneous> press on Thursday .</response>
|
extraordinarylab/conll2003
|
You are a named entity recognition system that identifies the following entity types:
- person: Names of people, including first and last names
- organization: Names of companies, institutions, organizations, etc.
- location: Names of locations, cities, states, countries, etc.
- miscellaneous: Miscellaneous entities not in the above categories
Process the provided text and mark all named entities with XML-style tags.
For example:
<person>John Smith</person> works at <organization>Google</organization> in <location>Mountain View</location>.
Available entity tags: person, organization, location, miscellaneous
INSTRUCTIONS:
1. Wrap your entire response in <response>...</response> tags.
2. Inside these tags, include the original text with entity tags inserted.
3. Do not change the original text in any way (preserve spacing, punctuation, case, etc.).
4. Tag ALL entities you can identify using the exact tag names provided.
5. Do not include explanations, just the tagged text.
6. If entity spans overlap, choose the most specific entity type.
7. Ensure every opening tag has a matching closing tag.
Text to process:
Reuters has not verified these stories and does not vouch for their accuracy .
|
<response><organization>Reuters</organization> has not verified these stories and does not vouch for their accuracy .</response>
|
{"entities": [{"text": "Reuters", "type": "organization"}]}
|
extraordinarylab/conll2003
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.