AI Knowledge Graph

Turn documents into a knowledge graph
of entities and relationships

Identify the important people, companies, organizations, assets, concepts and other entities in the evidence — then map the relationships explicitly supported by the documents.

Canonical entitiesEvidence-backed relationshipsAlias resolution

Start free · No card required · Uploaded files deleted after the task

See how the matter is connected

Identify entities explicitly mentioned in the evidence.

Resolve supported aliases and name variations to canonical entities.

Extract source, target, relationship and valid-from dates when available.

Preserve uncertainty instead of inventing links.

01

From document pile to connected structure

The Knowledge Graph skill extracts canonical entity names, types, concise descriptions and evidence-supported relationships.

02

Identity resolution without over-merging

Name variations can be resolved to one canonical entity when the evidence supports it. Ambiguous identities remain unresolved.

03

Relationships must be supported

Only relationships explicitly stated or unambiguously established by the evidence are included.

Frequently asked questions

Can it merge aliases?

Yes, when the evidence supports that the names refer to the same entity.

Will it invent relationships?

No.

Can relationships include dates?

Yes. A valid-from date is included when the evidence states or implies when the relationship began.

See the network hidden inside your documents

Upload your documents and run this skill in Continua.

Start free
First task free

Run Your First Investigation Free

Attach the file pile, ask the hard question, get back a cited report with every conflict flagged. No credit card. Two free tasks per week.

No credit card
2 free investigations / week
Zero document retention