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.