Triple

T16248574
Position Surface form Disambiguated ID Type / Status
Subject Midge Wood E394437 entity
Predicate screenWriterOfWork P25235 FINISHED
Object Alec Coppel E394432 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: Alec Coppel | Statement: [Midge Wood, screenWriterOfWork, Alec Coppel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alec Coppel
Context triple: [Midge Wood, screenWriterOfWork, Alec Coppel]
  • A. Alec Coppel chosen
    Alec Coppel was an Australian-born screenwriter and playwright best known for his work on classic suspense films, including contributing to the script of Alfred Hitchcock’s "Vertigo."
  • B. Gavin Koppell
    Gavin Koppell is a musician best known for his early role as a DJ and turntablist with the American rock band Incubus.
  • C. Michael McCloskey
    Michael McCloskey is a relatively obscure individual whose primary distinguishing feature is sharing the McCloskey surname, with no widely recognized public achievements or roles commonly associated with his name.
  • D. Chris Healey
    Chris Healey is a computer scientist known for his work in information visualization and visual analytics.
  • E. John Stockwell
    John Stockwell is an American film director, screenwriter, and actor known for helming stylish action and thriller films such as "Into the Blue."
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24594f23c8190bd59fcb2585cb5e3 completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a002d9de7548190974851dc54465f0b completed May 10, 2026, 7:02 a.m.
Created at: April 10, 2026, 5:04 a.m.