Triple

T15751938
Position Surface form Disambiguated ID Type / Status
Subject Tower Heist E381867 entity
Predicate storyBy P1955 FINISHED
Object Bill Collage E1052928 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: Bill Collage | Statement: [Tower Heist, storyBy, Bill Collage]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bill Collage
Context triple: [Tower Heist, storyBy, Bill Collage]
  • A. Bill Collage chosen
    Bill Collage is an American screenwriter known for co-writing major studio films such as Assassin's Creed and Exodus: Gods and Kings.
  • B. Nick Halsey
    Nick Halsey is the down-on-his-luck, alcoholic salesman whose life unravels and forces him to start over in the dark comedy-drama film "Everything Must Go."
  • C. Andrew McCollum
    Andrew McCollum is an American entrepreneur and software engineer best known as one of the original co-founders of Facebook.
  • D. Matthew Gross
    Matthew Gross is a television and film producer best known for his work on the ABC drama series "Dirty Sexy Money."
  • E. Matthew Gross
    Matthew Gross is a television producer best known for his work as an executive producer on the crime drama series "Body of Proof."
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e05030e31081908c307a8dc7067db4 completed April 16, 2026, 2:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff876f005c8190913dec49b839b9f9 completed May 9, 2026, 7:13 p.m.
Created at: April 10, 2026, 4:47 a.m.