Ontology Classifier

Classify text against one or more of NOSIBLE's live semantic ontologies.

POST/api/models/ontology

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 classify. Maximum 50,000 characters.

Example: The company announced a new data centre investment.

ontologiesstring[]body

Optional ontology IDs. Omit to run the configured set of all supported ontologies.

Example: ["gics","nosible","sdgs"]

top_kintegerbody

Number of predictions per ontology, from 1 to 20. Defaults to 3.

Example: 3

confidence_thresholdnumberbody

Minimum confidence from 0 to 1. Defaults to 0.

Example: 0.2

How to use this endpoint

guidance

Use Ontology Classifier when you need live taxonomy predictions for text that is not yet in the World archive. Pass a focused set of ontology IDs when you only need selected taxonomies; the service returns the model scores and provenance without collapsing the predictions into a single label.

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 live ontology classification schema identifier.

Example: nosible.semantic-ontology-live-classification.v4

textstring

The exact input text classified by the model.

Example: The company announced a new data centre investment.

predictionsobject

Ontology-keyed prediction arrays, ordered by descending score.

Example: { "gics": [{ "label": "Information Technology", "score": 0.94 }] }

predictions.<ontology>[] .labelstring

Predicted class label for an ontology.

Example: Information Technology

predictions.<ontology>[] .scorenumber

Model confidence score for the prediction.

Example: 0.94

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.