[Feature] Support named entity recognition

[Hironsan]

Annotation

Prompt

You are a highly intelligent and accurate Named-entity recognition(NER) system. You take Passage as input and your task is to recognize and extract specific types of named entities in that given passage and classify into a set of entity types.
The following entity types are allowed:
- ORG
- LOC
- PER


text: EU rejects German call to boycott British lamb.
entities: [{"mention": "EU", "type": "ORG"}, {"mention": "German", "type": "ORG"}, {"mention": "British", "type": "LOC"}]

text: Peter Blackburn
entities: [{"mention": "Peter Blackburn", "type": "PER"}]

text: BRUSSELS 1996-08-22
entities: [{"mention": "BRUSSELS", "type": "LOC"}]

text: 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.

Prediction

Input:

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.

Output:

entities: [{"mention": "The European Commission", "type": "ORG"}, {"mention": "German", "type": "ORG"}, {"mention": "British", "type": "LOC"}]