Ontology

Ground cognify extraction against an RDF/OWL, Turtle, or JSON-LD ontology so entities are matched to a known vocabulary.

What it does

Supplies an ontology (RDF/OWL, Turtle, or JSON-LD) to cognify so extracted entities are matched and grounded against a known vocabulary. The OntologyResolver loads the file and matches extracted entity names/types to ontology terms during knowledge-graph extraction.

When to use it

• You have a controlled vocabulary / taxonomy and want extraction to align with it (consistent entity types, canonical names).
• You want to constrain or normalize the messy free-form output of an LLM.

CLI

cognee-cli cognify exposes the ontology file directly:

cognee-cli cognify -d my_dataset --ontology-file ./ontologies/domain.owl

The flag is --ontology-file <path> (crates/cli/src/cli.rs, CognifyArgs).

Configuration (env / config keys)

You can also set the ontology globally instead of per-invocation:

Env var	Config key (alias)	Default
ONTOLOGY_FILE_PATH	ontology.file_path (ontology_file_path)	(empty)
ONTOLOGY_RESOLVER	ontology.resolver (ontology_resolver)	rdflib
ONTOLOGY_MATCHING_STRATEGY	ontology.matching_strategy (ontology_matching_strategy)	fuzzy

export ONTOLOGY_FILE_PATH=./ontologies/domain.owl
cognee-cli cognify -d my_dataset

ontology.resolver selects an OntologyResolverFactory on the component registry. Only rdflib (RDF/JSON-LD/Turtle) is built in, and it implements only the fuzzy matching strategy (it warns on any other). An external crate can add a resolver with ComponentRegistry::register_ontology_resolver. See Configuration: Ontology for the full surface.

Supported formats

RDF/OWL, Turtle, and JSON-LD, parsed via the sophia family of crates. See crates/ontology/ for the resolver implementations and the test fixtures under crates/ontology/tests/fixtures/.

Pointers

• crates/ontology/ — OntologyResolver, RdfLibOntologyResolver, NoOpOntologyResolver.
• crates/cli/src/cli.rs — --ontology-file.
• Configuration — ontology env vars.
• Operations — cognify stage.