Triple

T11328969
Position Surface form Disambiguated ID Type / Status
Subject Over the Hedge E268294 entity
Predicate screenwriter P2831 FINISHED
Object David Hoselton E667954 NE FINISHED

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: David Hoselton | Statement: [Over the Hedge, screenwriter, David Hoselton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Hoselton
Context triple: [Over the Hedge, screenwriter, David Hoselton]
  • A. David Hoselton chosen
    David Hoselton is a television writer and producer best known for his work on medical dramas such as "The Good Doctor."
  • B. David Horsey
    David Horsey is an American political cartoonist and commentator renowned for his incisive editorial cartoons and multiple Pulitzer Prize-winning work.
  • C. Andrew Rennison
    Andrew Rennison is a British public official known for serving as the inaugural Surveillance Camera Commissioner, overseeing the regulation and ethical use of CCTV and related surveillance technologies in the UK.
  • D. Greg Mathieson
    Greg Mathieson is an American keyboardist, composer, and producer known for his work in jazz, fusion, and pop music, collaborating with numerous prominent artists.
  • E. Andrew Holbrook
    Andrew Holbrook is a professional mixed martial artist known for competing in major promotions such as the UFC in the lightweight division.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aacb1f0881908c84a349fd1be047 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e9e330008190b75490efde01dc59 completed April 9, 2026, 6:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69f489dfb2c881908a6f6bcd8b2d1cdc completed May 1, 2026, 11:09 a.m.
Created at: April 8, 2026, 9:32 p.m.