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 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:
EU rejects German call to boycott British lamb .
|
{"entities": [{"text": "EU", "type": "organization"}, {"text": "German", "type": "miscellaneous"}, {"text": "British", "type": "miscellaneous"}]}
|
<response><organization>EU</organization> rejects <miscellaneous>German</miscellaneous> call to boycott <miscellaneous>British</miscellaneous> lamb .</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:
Peter Blackburn
|
{"entities": [{"text": "Peter Blackburn", "type": "person"}]}
|
<response><person>Peter Blackburn</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:
BRUSSELS 1996-08-22
|
{"entities": [{"text": "BRUSSELS", "type": "location"}]}
|
<response><location>BRUSSELS</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:
The European Commission said on Thursday it disagreed with German advice to consumers to shun British lamb until scientists determine whether mad cow disease can be transmitted to sheep .
|
<response>The <organization>European Commission</organization> said on Thursday it disagreed with <miscellaneous>German</miscellaneous> advice to consumers to shun <miscellaneous>British</miscellaneous> lamb until scientists determine whether mad cow disease can be transmitted to sheep .</response>
|
{"entities": [{"text": "European Commission", "type": "organization"}, {"text": "German", "type": "miscellaneous"}, {"text": "British", "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:
Germany 's representative to the European Union 's veterinary committee Werner Zwingmann said on Wednesday consumers should buy sheepmeat from countries other than Britain until the scientific advice was clearer .
|
{"entities": [{"text": "Germany", "type": "location"}, {"text": "European Union", "type": "organization"}, {"text": "Werner Zwingmann", "type": "person"}, {"text": "Britain", "type": "location"}]}
|
<response><location>Germany</location> 's representative to the <organization>European Union</organization> 's veterinary committee <person>Werner Zwingmann</person> said on Wednesday consumers should buy sheepmeat from countries other than <location>Britain</location> until the scientific advice was clearer .</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:
" We do n't support any such recommendation because we do n't see any grounds for it , " the Commission 's chief spokesman Nikolaus van der Pas told a news briefing .
|
{"entities": [{"text": "Commission", "type": "organization"}, {"text": "Nikolaus van der Pas", "type": "person"}]}
|
<response>" We do n't support any such recommendation because we do n't see any grounds for it , " the <organization>Commission</organization> 's chief spokesman <person>Nikolaus van der Pas</person> told a news briefing .</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:
He said further scientific study was required and if it was found that action was needed it should be taken by the European Union .
|
<response>He said further scientific study was required and if it was found that action was needed it should be taken by the <organization>European Union</organization> .</response>
|
{"entities": [{"text": "European Union", "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:
He said a proposal last month by EU Farm Commissioner Franz Fischler to ban sheep brains , spleens and spinal cords from the human and animal food chains was a highly specific and precautionary move to protect human health .
|
<response>He said a proposal last month by <organization>EU</organization> Farm Commissioner <person>Franz Fischler</person> to ban sheep brains , spleens and spinal cords from the human and animal food chains was a highly specific and precautionary move to protect human health .</response>
|
{"entities": [{"text": "EU", "type": "organization"}, {"text": "Franz Fischler", "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:
Fischler proposed EU-wide measures after reports from Britain and France that under laboratory conditions sheep could contract Bovine Spongiform Encephalopathy ( BSE ) -- mad cow disease .
|
{"entities": [{"text": "Fischler", "type": "person"}, {"text": "EU-wide", "type": "miscellaneous"}, {"text": "Britain", "type": "location"}, {"text": "France", "type": "location"}, {"text": "Bovine Spongiform Encephalopathy", "type": "miscellaneous"}, {"text": "BSE", "type": "miscellaneous"}]}
|
<response><person>Fischler</person> proposed <miscellaneous>EU-wide</miscellaneous> measures after reports from <location>Britain</location> and <location>France</location> that under laboratory conditions sheep could contract <miscellaneous>Bovine Spongiform Encephalopathy</miscellaneous> ( <miscellaneous>BSE</miscellaneous> ) -- mad cow disease .</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 Fischler agreed to review his proposal after the EU 's standing veterinary committee , mational animal health officials , questioned if such action was justified as there was only a slight risk to human health .
|
{"entities": [{"text": "Fischler", "type": "person"}, {"text": "EU", "type": "organization"}]}
|
<response>But <person>Fischler</person> agreed to review his proposal after the <organization>EU</organization> 's standing veterinary committee , mational animal health officials , questioned if such action was justified as there was only a slight risk to human health .</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:
Spanish Farm Minister Loyola de Palacio had earlier accused Fischler at an EU farm ministers ' meeting of causing unjustified alarm through " dangerous generalisation . "
|
{"entities": [{"text": "Spanish", "type": "miscellaneous"}, {"text": "Loyola de Palacio", "type": "person"}, {"text": "Fischler", "type": "person"}, {"text": "EU", "type": "organization"}]}
|
<response><miscellaneous>Spanish</miscellaneous> Farm Minister <person>Loyola de Palacio</person> had earlier accused <person>Fischler</person> at an <organization>EU</organization> farm ministers ' meeting of causing unjustified alarm through " dangerous generalisation . "</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:
.
|
{"entities": []}
|
<response>.</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:
Only France and Britain backed Fischler 's proposal .
|
{"entities": [{"text": "France", "type": "location"}, {"text": "Britain", "type": "location"}, {"text": "Fischler", "type": "person"}]}
|
<response>Only <location>France</location> and <location>Britain</location> backed <person>Fischler</person> 's proposal .</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 EU 's scientific veterinary and multidisciplinary committees are due to re-examine the issue early next month and make recommendations to the senior veterinary officials .
|
<response>The <organization>EU</organization> 's scientific veterinary and multidisciplinary committees are due to re-examine the issue early next month and make recommendations to the senior veterinary officials .</response>
|
{"entities": [{"text": "EU", "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:
Sheep have long been known to contract scrapie , a brain-wasting disease similar to BSE which is believed to have been transferred to cattle through feed containing animal waste .
|
<response>Sheep have long been known to contract scrapie , a brain-wasting disease similar to <miscellaneous>BSE</miscellaneous> which is believed to have been transferred to cattle through feed containing animal waste .</response>
|
{"entities": [{"text": "BSE", "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:
British farmers denied on Thursday there was any danger to human health from their sheep , but expressed concern that German government advice to consumers to avoid British lamb might influence consumers across Europe .
|
<response><miscellaneous>British</miscellaneous> farmers denied on Thursday there was any danger to human health from their sheep , but expressed concern that <miscellaneous>German</miscellaneous> government advice to consumers to avoid <miscellaneous>British</miscellaneous> lamb might influence consumers across <location>Europe</location> .</response>
|
{"entities": [{"text": "British", "type": "miscellaneous"}, {"text": "German", "type": "miscellaneous"}, {"text": "British", "type": "miscellaneous"}, {"text": "Europe", "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:
" What we have to be extremely careful of is how other countries are going to take Germany 's lead , " Welsh National Farmers ' Union ( NFU ) chairman John Lloyd Jones said on BBC radio .
|
<response>" What we have to be extremely careful of is how other countries are going to take <location>Germany</location> 's lead , " <organization>Welsh National Farmers ' Union</organization> ( <organization>NFU</organization> ) chairman <person>John Lloyd Jones</person> said on <organization>BBC radio</organization> .</response>
|
{"entities": [{"text": "Germany", "type": "location"}, {"text": "Welsh National Farmers ' Union", "type": "organization"}, {"text": "NFU", "type": "organization"}, {"text": "John Lloyd Jones", "type": "person"}, {"text": "BBC 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 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:
Bonn has led efforts to protect public health after consumer confidence collapsed in March after a British report suggested humans could contract an illness similar to mad cow disease by eating contaminated beef .
|
<response><location>Bonn</location> has led efforts to protect public health after consumer confidence collapsed in March after a <miscellaneous>British</miscellaneous> report suggested humans could contract an illness similar to mad cow disease by eating contaminated beef .</response>
|
{"entities": [{"text": "Bonn", "type": "location"}, {"text": "British", "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:
Germany imported 47,600 sheep from Britain last year , nearly half of total imports .
|
<response><location>Germany</location> imported 47,600 sheep from <location>Britain</location> last year , nearly half of total imports .</response>
|
{"entities": [{"text": "Germany", "type": "location"}, {"text": "Britain", "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 brought in 4,275 tonnes of British mutton , some 10 percent of overall imports .
|
{"entities": [{"text": "British", "type": "miscellaneous"}]}
|
<response>It brought in 4,275 tonnes of <miscellaneous>British</miscellaneous> mutton , some 10 percent of overall imports .</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:
Rare Hendrix song draft sells for almost $ 17,000 .
|
<response>Rare <person>Hendrix</person> song draft sells for almost $ 17,000 .</response>
|
{"entities": [{"text": "Hendrix", "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:
LONDON 1996-08-22
|
{"entities": [{"text": "LONDON", "type": "location"}]}
|
<response><location>LONDON</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:
A rare early handwritten draft of a song by U.S. guitar legend Jimi Hendrix was sold for almost $ 17,000 on Thursday at an auction of some of the late musician 's favourite possessions .
|
{"entities": [{"text": "U.S.", "type": "location"}, {"text": "Jimi Hendrix", "type": "person"}]}
|
<response>A rare early handwritten draft of a song by <location>U.S.</location> guitar legend <person>Jimi Hendrix</person> was sold for almost $ 17,000 on Thursday at an auction of some of the late musician 's favourite possessions .</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 Florida restaurant paid 10,925 pounds ( $ 16,935 ) for the draft of " Ai n't no telling " , which Hendrix penned on a piece of London hotel stationery in late 1966 .
|
<response>A <location>Florida</location> restaurant paid 10,925 pounds ( $ 16,935 ) for the draft of " <miscellaneous>Ai n't no telling</miscellaneous> " , which <person>Hendrix</person> penned on a piece of <location>London</location> hotel stationery in late 1966 .</response>
|
{"entities": [{"text": "Florida", "type": "location"}, {"text": "Ai n't no telling", "type": "miscellaneous"}, {"text": "Hendrix", "type": "person"}, {"text": "London", "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:
At the end of a January 1967 concert in the English city of Nottingham he threw the sheet of paper into the audience , where it was retrieved by a fan .
|
<response>At the end of a January 1967 concert in the <miscellaneous>English</miscellaneous> city of <location>Nottingham</location> he threw the sheet of paper into the audience , where it was retrieved by a fan .</response>
|
{"entities": [{"text": "English", "type": "miscellaneous"}, {"text": "Nottingham", "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:
Buyers also snapped up 16 other items that were put up for auction by Hendrix 's former girlfriend Kathy Etchingham , who lived with him from 1966 to 1969 .
|
{"entities": [{"text": "Hendrix", "type": "person"}, {"text": "Kathy Etchingham", "type": "person"}]}
|
<response>Buyers also snapped up 16 other items that were put up for auction by <person>Hendrix</person> 's former girlfriend <person>Kathy Etchingham</person> , who lived with him from 1966 to 1969 .</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:
They included a black lacquer and mother of pearl inlaid box used by Hendrix to store his drugs , which an anonymous Australian purchaser bought for 5,060 pounds ( $ 7,845 ) .
|
<response>They included a black lacquer and mother of pearl inlaid box used by <person>Hendrix</person> to store his drugs , which an anonymous <miscellaneous>Australian</miscellaneous> purchaser bought for 5,060 pounds ( $ 7,845 ) .</response>
|
{"entities": [{"text": "Hendrix", "type": "person"}, {"text": "Australian", "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 guitarist died of a drugs overdose in 1970 aged 27 .
|
<response>The guitarist died of a drugs overdose in 1970 aged 27 .</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:
China says Taiwan spoils atmosphere for talks .
|
<response><location>China</location> says <location>Taiwan</location> spoils atmosphere for talks .</response>
|
{"entities": [{"text": "China", "type": "location"}, {"text": "Taiwan", "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:
BEIJING 1996-08-22
|
{"entities": [{"text": "BEIJING", "type": "location"}]}
|
<response><location>BEIJING</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:
China on Thursday accused Taipei of spoiling the atmosphere for a resumption of talks across the Taiwan Strait with a visit to Ukraine by Taiwanese Vice President Lien Chan this week that infuriated Beijing .
|
{"entities": [{"text": "China", "type": "location"}, {"text": "Taipei", "type": "location"}, {"text": "Taiwan Strait", "type": "location"}, {"text": "Ukraine", "type": "location"}, {"text": "Taiwanese", "type": "miscellaneous"}, {"text": "Lien Chan", "type": "person"}, {"text": "Beijing", "type": "location"}]}
|
<response><location>China</location> on Thursday accused <location>Taipei</location> of spoiling the atmosphere for a resumption of talks across the <location>Taiwan Strait</location> with a visit to <location>Ukraine</location> by <miscellaneous>Taiwanese</miscellaneous> Vice President <person>Lien Chan</person> this week that infuriated <location>Beijing</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:
Speaking only hours after Chinese state media said the time was right to engage in political talks with Taiwan , Foreign Ministry spokesman Shen Guofang told Reuters : " The necessary atmosphere for the opening of the talks has been disrupted by the Taiwan authorities . "
|
<response>Speaking only hours after <miscellaneous>Chinese</miscellaneous> state media said the time was right to engage in political talks with <location>Taiwan</location> , <organization>Foreign Ministry</organization> spokesman <person>Shen Guofang</person> told <organization>Reuters</organization> : " The necessary atmosphere for the opening of the talks has been disrupted by the <location>Taiwan</location> authorities . "</response>
|
{"entities": [{"text": "Chinese", "type": "miscellaneous"}, {"text": "Taiwan", "type": "location"}, {"text": "Foreign Ministry", "type": "organization"}, {"text": "Shen Guofang", "type": "person"}, {"text": "Reuters", "type": "organization"}, {"text": "Taiwan", "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:
State media quoted China 's top negotiator with Taipei , Tang Shubei , as telling a visiting group from Taiwan on Wednesday that it was time for the rivals to hold political talks .
|
{"entities": [{"text": "China", "type": "location"}, {"text": "Taipei", "type": "location"}, {"text": "Tang Shubei", "type": "person"}, {"text": "Taiwan", "type": "location"}]}
|
<response>State media quoted <location>China</location> 's top negotiator with <location>Taipei</location> , <person>Tang Shubei</person> , as telling a visiting group from <location>Taiwan</location> on Wednesday that it was time for the rivals to hold political talks .</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:
" Now is the time for the two sides to engage in political talks ...
|
<response>" Now is the time for the two sides to engage in political talks ...</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:
that is to end the state of hostility , " Thursday 's overseas edition of the People 's Daily quoted Tang as saying .
|
<response>that is to end the state of hostility , " Thursday 's overseas edition of the <organization>People 's Daily</organization> quoted <person>Tang</person> as saying .</response>
|
{"entities": [{"text": "People 's Daily", "type": "organization"}, {"text": "Tang", "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:
The foreign ministry 's Shen told Reuters Television in an interview he had read reports of Tang 's comments but gave no details of why the negotiator had considered the time right for talks with Taiwan , which Beijing considers a renegade province .
|
<response>The foreign ministry 's <organization>Shen</organization> told <organization>Reuters Television</organization> in an interview he had read reports of <person>Tang</person> 's comments but gave no details of why the negotiator had considered the time right for talks with <location>Taiwan</location> , which <location>Beijing</location> considers a renegade province .</response>
|
{"entities": [{"text": "Shen", "type": "organization"}, {"text": "Reuters Television", "type": "organization"}, {"text": "Tang", "type": "person"}, {"text": "Taiwan", "type": "location"}, {"text": "Beijing", "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:
China , which has long opposed all Taipei efforts to gain greater international recognition , was infuriated by a visit to Ukraine this week by Taiwanese Vice President Lien .
|
{"entities": [{"text": "China", "type": "location"}, {"text": "Taipei", "type": "location"}, {"text": "Ukraine", "type": "location"}, {"text": "Taiwanese", "type": "miscellaneous"}, {"text": "Lien", "type": "person"}]}
|
<response><location>China</location> , which has long opposed all <location>Taipei</location> efforts to gain greater international recognition , was infuriated by a visit to <location>Ukraine</location> this week by <miscellaneous>Taiwanese</miscellaneous> Vice President <person>Lien</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:
China says time right for Taiwan talks .
|
{"entities": [{"text": "China", "type": "location"}, {"text": "Taiwan", "type": "location"}]}
|
<response><location>China</location> says time right for <location>Taiwan</location> talks .</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:
BEIJING 1996-08-22
|
{"entities": [{"text": "BEIJING", "type": "location"}]}
|
<response><location>BEIJING</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:
China has said it was time for political talks with Taiwan and that the rival island should take practical steps towards that goal .
|
<response><location>China</location> has said it was time for political talks with <location>Taiwan</location> and that the rival island should take practical steps towards that goal .</response>
|
{"entities": [{"text": "China", "type": "location"}, {"text": "Taiwan", "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:
Consultations should be held to set the time and format of the talks , the official Xinhua news agency quoted Tang Shubei , executive vice chairman of the Association for Relations Across the Taiwan Straits , as saying late on Wednesday .
|
{"entities": [{"text": "Xinhua", "type": "organization"}, {"text": "Tang Shubei", "type": "person"}, {"text": "Association for Relations Across the Taiwan Straits", "type": "organization"}]}
|
<response>Consultations should be held to set the time and format of the talks , the official <organization>Xinhua</organization> news agency quoted <person>Tang Shubei</person> , executive vice chairman of the <organization>Association for Relations Across the Taiwan Straits</organization> , as saying late on Wednesday .</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:
German July car registrations up 14.2 pct yr / yr .
|
<response><miscellaneous>German</miscellaneous> July car registrations up 14.2 pct yr / yr .</response>
|
{"entities": [{"text": "German", "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:
FRANKFURT 1996-08-22
|
{"entities": [{"text": "FRANKFURT", "type": "location"}]}
|
<response><location>FRANKFURT</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:
German first-time registrations of motor vehicles jumped 14.2 percent in July this year from the year-earlier period , the Federal office for motor vehicles said on Thursday .
|
<response><miscellaneous>German</miscellaneous> first-time registrations of motor vehicles jumped 14.2 percent in July this year from the year-earlier period , the <organization>Federal office for motor vehicles</organization> said on Thursday .</response>
|
{"entities": [{"text": "German", "type": "miscellaneous"}, {"text": "Federal office for motor vehicles", "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:
The office said 356,725 new cars were registered in July 1996 -- 304,850 passenger cars and 15,613 trucks .
|
<response>The office said 356,725 new cars were registered in July 1996 -- 304,850 passenger cars and 15,613 trucks .</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 figures represent a 13.6 percent increase for passenger cars and a 2.2 percent decline for trucks from July 1995 .
|
{"entities": []}
|
<response>The figures represent a 13.6 percent increase for passenger cars and a 2.2 percent decline for trucks from July 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:
Motor-bike registration rose 32.7 percent in the period .
|
<response>Motor-bike registration rose 32.7 percent in the period .</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 growth was partly due to an increased number of Germans buying German cars abroad , while manufacturers said that domestic demand was weak , the federal office said .
|
{"entities": [{"text": "Germans", "type": "miscellaneous"}, {"text": "German", "type": "miscellaneous"}]}
|
<response>The growth was partly due to an increased number of <miscellaneous>Germans</miscellaneous> buying <miscellaneous>German</miscellaneous> cars abroad , while manufacturers said that domestic demand was weak , the federal 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 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:
Almost all German car manufacturers posted gains in registration numbers in the period .
|
<response>Almost all <miscellaneous>German</miscellaneous> car manufacturers posted gains in registration numbers in the period .</response>
|
{"entities": [{"text": "German", "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:
Volkswagen AG won 77,719 registrations , slightly more than a quarter of the total .
|
{"entities": [{"text": "Volkswagen AG", "type": "organization"}]}
|
<response><organization>Volkswagen AG</organization> won 77,719 registrations , slightly more than a quarter of the total .</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:
Opel AG together with General Motors came in second place with 49,269 registrations , 16.4 percent of the overall figure .
|
<response><organization>Opel AG</organization> together with <organization>General Motors</organization> came in second place with 49,269 registrations , 16.4 percent of the overall figure .</response>
|
{"entities": [{"text": "Opel AG", "type": "organization"}, {"text": "General Motors", "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:
Third was Ford with 35,563 registrations , or 11.7 percent .
|
{"entities": [{"text": "Ford", "type": "organization"}]}
|
<response>Third was <organization>Ford</organization> with 35,563 registrations , or 11.7 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:
Only Seat and Porsche had fewer registrations in July 1996 compared to last year 's July .
|
<response>Only <organization>Seat</organization> and <organization>Porsche</organization> had fewer registrations in July 1996 compared to last year 's July .</response>
|
{"entities": [{"text": "Seat", "type": "organization"}, {"text": "Porsche", "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:
Seat posted 3,420 registrations compared with 5522 registrations in July a year earlier .
|
{"entities": [{"text": "Seat", "type": "organization"}]}
|
<response><organization>Seat</organization> posted 3,420 registrations compared with 5522 registrations in July a year earlier .</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:
Porsche 's registrations fell to 554 from 643 .
|
{"entities": [{"text": "Porsche", "type": "organization"}]}
|
<response><organization>Porsche</organization> 's registrations fell to 554 from 643 .</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:
GREEK SOCIALISTS GIVE GREEN LIGHT TO PM FOR ELECTIONS .
|
<response><miscellaneous>GREEK</miscellaneous> SOCIALISTS GIVE GREEN LIGHT TO PM FOR ELECTIONS .</response>
|
{"entities": [{"text": "GREEK", "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:
ATHENS 1996-08-22
|
<response><location>ATHENS</location> 1996-08-22</response>
|
{"entities": [{"text": "ATHENS", "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 Greek socialist party 's executive bureau gave the green light to Prime Minister Costas Simitis to call snap elections , its general secretary Costas Skandalidis told reporters .
|
{"entities": [{"text": "Greek", "type": "miscellaneous"}, {"text": "Costas Simitis", "type": "person"}, {"text": "Costas Skandalidis", "type": "person"}]}
|
<response>The <miscellaneous>Greek</miscellaneous> socialist party 's executive bureau gave the green light to Prime Minister <person>Costas Simitis</person> to call snap elections , its general secretary <person>Costas Skandalidis</person> 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 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:
Prime Minister Costas Simitis is going to make an official announcement after a cabinet meeting later on Thursday , said Skandalidis .
|
<response>Prime Minister <person>Costas Simitis</person> is going to make an official announcement after a cabinet meeting later on Thursday , said <person>Skandalidis</person> .</response>
|
{"entities": [{"text": "Costas Simitis", "type": "person"}, {"text": "Skandalidis", "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:
-- Dimitris Kontogiannis , Athens Newsroom +301 3311812-4
|
<response>-- <person>Dimitris Kontogiannis</person> , <organization>Athens Newsroom</organization> +301 3311812-4</response>
|
{"entities": [{"text": "Dimitris Kontogiannis", "type": "person"}, {"text": "Athens Newsroom", "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:
BayerVB sets C$ 100 million six-year bond .
|
{"entities": [{"text": "BayerVB", "type": "organization"}, {"text": "C$", "type": "miscellaneous"}]}
|
<response><organization>BayerVB</organization> sets <miscellaneous>C$</miscellaneous> 100 million six-year bond .</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:
LONDON 1996-08-22
|
<response><location>LONDON</location> 1996-08-22</response>
|
{"entities": [{"text": "LONDON", "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 following bond was announced by lead manager Toronto Dominion .
|
{"entities": [{"text": "Toronto Dominion", "type": "person"}]}
|
<response>The following bond was announced by lead manager <person>Toronto Dominion</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:
BORROWER BAYERISCHE VEREINSBANK
|
<response>BORROWER <organization>BAYERISCHE VEREINSBANK</organization></response>
|
{"entities": [{"text": "BAYERISCHE VEREINSBANK", "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:
AMT C$ 100 MLN COUPON 6.625 MATURITY 24.SEP.02
|
{"entities": [{"text": "C$", "type": "miscellaneous"}]}
|
<response>AMT <miscellaneous>C$</miscellaneous> 100 MLN COUPON 6.625 MATURITY 24.SEP.02</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:
TYPE STRAIGHT ISS PRICE 100.92 PAY DATE 24.SEP.96
|
{"entities": []}
|
<response>TYPE STRAIGHT ISS PRICE 100.92 PAY DATE 24.SEP.96</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:
FULL FEES 1.875 REOFFER 99.32 SPREAD +20 BP
|
{"entities": []}
|
<response>FULL FEES 1.875 REOFFER 99.32 SPREAD +20 BP</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:
MOODY AA1 LISTING LUX PAY FREQ =
|
<response>MOODY AA1 LISTING LUX PAY FREQ =</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:
S&P = DENOMS ( K ) 1-10-100 SALE LIMITS US / UK / CA
|
<response><organization>S&P</organization> = DENOMS ( K ) 1-10-100 SALE LIMITS <location>US</location> / <location>UK</location> / <location>CA</location></response>
|
{"entities": [{"text": "S&P", "type": "organization"}, {"text": "US", "type": "location"}, {"text": "UK", "type": "location"}, {"text": "CA", "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:
NEG PLG NO CRS DEFLT NO FORCE MAJ =
|
{"entities": []}
|
<response>NEG PLG NO CRS DEFLT NO FORCE MAJ =</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:
GOV LAW GERMAN HOME CTRY = TAX PROVS STANDARD
|
<response>GOV LAW <miscellaneous>GERMAN</miscellaneous> HOME CTRY = TAX PROVS STANDARD</response>
|
{"entities": [{"text": "GERMAN", "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:
MGT / UND 0.275 SELL CONC 1.60 PRAECIP =
|
<response>MGT / UND 0.275 SELL CONC 1.60 PRAECIP =</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:
UNDERLYING GOVT BOND 7.0 PCT SEPT 2001
|
{"entities": []}
|
<response>UNDERLYING GOVT BOND 7.0 PCT SEPT 2001</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:
NOTES BAYERISCHE VEREINSBANK IS JOINT LEAD MANAGER
|
{"entities": [{"text": "BAYERISCHE VEREINSBANK", "type": "organization"}]}
|
<response>NOTES <organization>BAYERISCHE VEREINSBANK</organization> IS JOINT LEAD MANAGER</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:
-- London Newsroom +44 171 542 7658
|
{"entities": [{"text": "London Newsroom", "type": "organization"}]}
|
<response>-- <organization>London Newsroom</organization> +44 171 542 7658</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:
Venantius sets $ 300 million January 1999 FRN .
|
{"entities": [{"text": "Venantius", "type": "organization"}]}
|
<response><organization>Venantius</organization> sets $ 300 million January 1999 FRN .</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:
LONDON 1996-08-22
|
<response><location>LONDON</location> 1996-08-22</response>
|
{"entities": [{"text": "LONDON", "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:
The following floating-rate issue was announced by lead manager Lehman Brothers International .
|
<response>The following floating-rate issue was announced by lead manager <organization>Lehman Brothers International</organization> .</response>
|
{"entities": [{"text": "Lehman Brothers International", "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:
BORROWER VENANTIUS AB ( SWEDISH NATIONAL MORTGAGE AGENCY )
|
<response>BORROWER <organization>VENANTIUS AB</organization> ( <miscellaneous>SWEDISH</miscellaneous> NATIONAL MORTGAGE AGENCY )</response>
|
{"entities": [{"text": "VENANTIUS AB", "type": "organization"}, {"text": "SWEDISH", "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:
AMT $ 300 MLN SPREAD - 12.5 BP MATURITY 21.JAN.99
|
<response>AMT $ 300 MLN SPREAD - 12.5 BP MATURITY 21.JAN.99</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:
TYPE FRN BASE 3M LIBOR PAY DATE S23.SEP.96
|
<response>TYPE FRN BASE <organization>3M</organization> LIBOR PAY DATE S23.SEP.96</response>
|
{"entities": [{"text": "3M", "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:
LAST MOODY AA3 ISS PRICE 99.956 FULL FEES 10 BP
|
{"entities": []}
|
<response>LAST MOODY AA3 ISS PRICE 99.956 FULL FEES 10 BP</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 S&P AA+ REOFFER =
|
<response>LAST <organization>S&P</organization> AA+ REOFFER =</response>
|
{"entities": [{"text": "S&P", "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:
NOTES S SHORT FIRST COUPON
|
{"entities": []}
|
<response>NOTES S SHORT FIRST COUPON</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:
LISTING LONDON DENOMS ( K ) 1-10-100 SALE LIMITS US / UK / JP / FR
|
<response>LISTING <location>LONDON</location> DENOMS ( K ) 1-10-100 SALE LIMITS <location>US</location> / <location>UK</location> / <location>JP</location> / <location>FR</location></response>
|
{"entities": [{"text": "LONDON", "type": "location"}, {"text": "US", "type": "location"}, {"text": "UK", "type": "location"}, {"text": "JP", "type": "location"}, {"text": "FR", "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:
NEG PLG YES CRS DEFLT NO FORCE MAJ IPMA 2
|
<response>NEG PLG YES CRS DEFLT NO FORCE MAJ IPMA 2</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:
GOV LAW ENGLISH HOME CTRY SWEDEN TAX PROVS STANDARD
|
{"entities": [{"text": "ENGLISH", "type": "miscellaneous"}, {"text": "SWEDEN", "type": "location"}]}
|
<response>GOV LAW <miscellaneous>ENGLISH</miscellaneous> HOME CTRY <location>SWEDEN</location> TAX PROVS STANDARD</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:
MGT / UND 5 BP SELL CONC 5 BP PRAECIP =
|
{"entities": []}
|
<response>MGT / UND 5 BP SELL CONC 5 BP PRAECIP =</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:
NOTES ISSUED OFF EMTN PROGRAMME
|
{"entities": []}
|
<response>NOTES ISSUED OFF EMTN PROGRAMME</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:
-- London Newsroom +44 171 542 8863
|
{"entities": [{"text": "London Newsroom", "type": "organization"}]}
|
<response>-- <organization>London Newsroom</organization> +44 171 542 8863</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:
Port conditions update - Syria - Lloyds Shipping .
|
{"entities": [{"text": "Syria", "type": "location"}, {"text": "Lloyds Shipping", "type": "organization"}]}
|
<response>Port conditions update - <location>Syria</location> - <organization>Lloyds Shipping</organization> .</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:
Port conditions from Lloyds Shipping Intelligence Service --
|
{"entities": [{"text": "Lloyds Shipping Intelligence Service", "type": "organization"}]}
|
<response>Port conditions from <organization>Lloyds Shipping Intelligence Service</organization> --</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:
LATTAKIA , Aug 10 - waiting time at Lattakia and Tartous presently 24 hours .
|
<response><location>LATTAKIA</location> , Aug 10 - waiting time at <location>Lattakia</location> and <location>Tartous</location> presently 24 hours .</response>
|
{"entities": [{"text": "LATTAKIA", "type": "location"}, {"text": "Lattakia", "type": "location"}, {"text": "Tartous", "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:
Israel plays down fears of war with Syria .
|
<response><location>Israel</location> plays down fears of war with <location>Syria</location> .</response>
|
{"entities": [{"text": "Israel", "type": "location"}, {"text": "Syria", "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:
Colleen Siegel
|
{"entities": [{"text": "Colleen Siegel", "type": "person"}]}
|
<response><person>Colleen Siegel</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:
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 's outgoing peace negotiator with Syria said on Thursday current tensions between the two countries appeared to be a storm in a teacup .
|
{"entities": [{"text": "Israel", "type": "location"}, {"text": "Syria", "type": "location"}]}
|
<response><location>Israel</location> 's outgoing peace negotiator with <location>Syria</location> said on Thursday current tensions between the two countries appeared to be a storm in a teacup .</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:
Itamar Rabinovich , who as Israel 's ambassador to Washington conducted unfruitful negotiations with Syria , told Israel Radio it looked like Damascus wanted to talk rather than fight .
|
{"entities": [{"text": "Itamar Rabinovich", "type": "person"}, {"text": "Israel", "type": "location"}, {"text": "Washington", "type": "location"}, {"text": "Syria", "type": "location"}, {"text": "Israel Radio", "type": "organization"}, {"text": "Damascus", "type": "location"}]}
|
<response><person>Itamar Rabinovich</person> , who as <location>Israel</location> 's ambassador to <location>Washington</location> conducted unfruitful negotiations with <location>Syria</location> , told <organization>Israel Radio</organization> it looked like <location>Damascus</location> wanted to talk rather than fight .</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 appears to me the Syrian priority is still to negotiate .
|
{"entities": [{"text": "Syrian", "type": "miscellaneous"}]}
|
<response>" It appears to me the <miscellaneous>Syrian</miscellaneous> priority is still to negotiate .</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 Syrians are confused , they are definitely tense , but the general assessment here in Washington is that this is essentially a storm in a teacup , " he said .
|
<response>The <miscellaneous>Syrians</miscellaneous> are confused , they are definitely tense , but the general assessment here in <location>Washington</location> is that this is essentially a storm in a teacup , " he said .</response>
|
{"entities": [{"text": "Syrians", "type": "miscellaneous"}, {"text": "Washington", "type": "location"}]}
|
extraordinarylab/conll2003
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 30