Skip to content

Generative AI & LLMs

Relation extraction

Finding connections between people, organizations or things mentioned in writing.

Example

A system extracts that one company acquired another.

Why people use it

It helps turn writing into records of who did what or how things are connected.

What you'll hear

“Which company acquired which other company?”

What this means for you

Check direction, negation and background information in extracted relationships.

Can you control it?

Developer-only

The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.

Common questions

Does detecting two names establish their relationship?
No. The language connecting them must be interpreted correctly.
Can it reverse the direction of a relationship?
Yes. Confusing buyer and seller, for example, creates a different claim.
Can a denied relationship be mistaken for a real one?
Yes. Missing a word such as 'not' can turn a denial into an incorrect fact.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice