Named Entity Recognition

Extract multilingual PERSON, ORG, GPE, LOC, and PRODUCT entities from text.

POST/api/models/ner

Related NOSIBLE resources

research & data

Explore the NOSIBLE World interface, inspect the World data dictionary, and browse the classification ontologies used by World.

Authorizations

Bearer

Authorizationstringrequiredheader

Required Bearer API key. Programmatic access to the World API needs a key; browsing nosible.world in a browser does not.

Example: Bearer nos_sk_...

Body

application/json

textstringrequiredbody

Text to analyse. Maximum 8,000 characters.

Example: NVIDIA opened a new office in Johannesburg.

thresholdnumberbody

Entity confidence threshold from 0 to 1. Defaults to 0.6.

Example: 0.6

How to use this endpoint

guidance

Use Named Entity Recognition to extract the fixed GLiNER label set from multilingual text before resolving entities or constructing World filters. Entity offsets are Python-style half-open character spans: start is inclusive and end is exclusive. Keep the original text unchanged when using the offsets.

Response body

application/json

These are the fields you can build against. Nested names use dot notation; optional sections are called out in their descriptions.

results[] .textstring

The exact input text for the result.

Example: NVIDIA opened a new office in Johannesburg.

results[] .entitiesobject[]

Entities detected in the text, using PERSON, ORG, GPE, LOC, or PRODUCT labels.

Example: [{ "start": 0, "end": 6, "text": "NVIDIA", "label": "ORG", "score": 0.99 }]

results[].entities[].start/endinteger

Half-open character offsets into the exact input text.

Example: 0 / 6

results[].entities[].textstring

The entity surface text.

Example: NVIDIA

results[].entities[].labelenum

One of PERSON, ORG, GPE, LOC, or PRODUCT.

Example: ORG

results[].entities[].scorenumber

Model confidence score.

Example: 0.99

model_provenance.nerstring

NER checkpoint used by the model service.

Example: NOSIBLE/gliner-ner-v1

Responses and errors

HTTP

200Request succeeded. The response body is shown in the panel on the right.

400invalid_request — The request is syntactically valid JSON but a value, date, filter, or combination of fields is invalid.

401unauthorized — The required API key or Bearer credential is missing or invalid.

422validation_error — The request shape is understood but one or more values fail validation.

429rate_limited — The request exceeded the account or public-window rate limit. Respect Retry-After when supplied.

502upstream_error — An upstream retrieval service failed while processing the request.

504upstream_timeout — An upstream retrieval service did not respond within the request timeout.