​
What is an ontology in Cognee?

An ontology is an optional RDF/OWL file you can provide to Cognee. It acts as a reference vocabulary, making sure that entity types (“classes”) and entity mentions (“individuals”) extracted from your data are linked to canonical, well-defined concepts. Think of it as adding a dictionary or schema to guide how your graph is built.

​
How it works

  • You pass ontology_file_path="my_ontology.owl" when running Cognify.
  • Cognee parses the file with RDFLib and loads its classes and relationships.
  • During graph extraction, entities and types are checked against the ontology:
    • If a match is found, the node is marked ontology_valid=True.
    • Parent classes and object-property links from the ontology are attached as extra edges.
  • If no ontology is provided, extraction still works, just without validation or enrichment.

​
Why use an ontology

  • Consistency: standardize how entities and types are represented
  • Enrichment: bring in inherited relationships from a domain schema
  • Control: align Cognee’s graph with existing enterprise or scientific vocabularies

​
Supported formats

Any format RDFLib can parse:
  • RDF/XML (.owl, .rdf)
  • Turtle (.ttl)
  • N-Triples, JSON-LD, and others

​
When to skip it

  • If you don’t supply one, Cognee still extracts nodes and edges.
  • Ontology fields will just remain unvalidated, and no extra structure is added.

Cognify

Where the ontology is applied during graph extraction

Search

How enriched graphs improve query results

Architecture

How external vocabularies integrate into Cognee’s pipeline