Named Entity Recognition (batch)

Extract entities from up to 64 English texts in one request.

POST/api/models/ner/batch

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

textsstring[]requiredbody

Between 1 and 64 English texts, each at most 8,000 characters.

Example: ["NVIDIA opened a new office in Johannesburg.","SAP expanded in Berlin."]

How to use this endpoint

guidance

Use Named Entity Recognition (batch) when you have multiple English texts to classify. This fine-tune is trained for English. Each item in results uses the same text and predictions shape as the single-text NER response, in the same order as the request.

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.

schemastring

Stable classifier response schema shared by the NER endpoints.

Example: nosible_model_classification_v1

modelstring

Pinned classifier name, version, and immutable build identifier.

Example: NOSIBLE/gliner-ner-v1@revision:d306c21d9c56b6688a5353e091ddb04d37b2b3f9

resultsobject[]

One NER result per input text, in input order.

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

results[].textstring

The exact input text classified for this result.

Example: NVIDIA opened a new office in Johannesburg.

results[].predictionsobject[]

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

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

results[].predictions[].labelenum

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

Example: ORG

results[].predictions[].scorenumber

Model confidence score.

Example: 0.99

results[].predictions[].textstring

The entity surface text.

Example: NVIDIA

results[].predictions[].start/endinteger

Half-open character offsets into the exact input text.

Example: 0 / 6

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.