Triple

T20297165
Position Surface form Disambiguated ID Type / Status
Subject Frank Ligourin E505379 entity
Predicate hasScreenwriter P62466 FINISHED
Object Andy Lewis NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Andy Lewis | Statement: [Frank Ligourin, hasScreenwriter, Andy Lewis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andy Lewis
Context triple: [Frank Ligourin, hasScreenwriter, Andy Lewis]
  • A. Andy Lewis chosen
    Andy Lewis was an American screenwriter best known for co-writing the acclaimed 1971 crime thriller film "Klute."
  • B. Andy Lewis
    Andy Lewis is a British musician and producer best known as a bassist and collaborator in the UK mod and soul revival scene.
  • C. Tim Lewis
    Tim Lewis is an American football coach and former NFL defensive back best known for his coaching roles at the professional and collegiate levels.
  • D. Andrew Lewis
    Andrew Lewis was an 18th-century American pioneer, surveyor, and military leader in the French and Indian War and the American Revolutionary War, noted for his role in the Battle of Point Pleasant.
  • E. Mike Lewis
    Mike Lewis is a musician best known for having been an early member of the indie rock band Yo La Tengo.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e677095fb481909806214da4002b59 completed April 20, 2026, 6:57 p.m.
Created at: April 16, 2026, 11:16 a.m.