Triple

T13516086
Position Surface form Disambiguated ID Type / Status
Subject Holy Smoke! E322762 entity
Predicate producer P490 FINISHED
Object Jan Chapman E118657 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: Jan Chapman | Statement: [Holy Smoke!, producer, Jan Chapman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jan Chapman
Context triple: [Holy Smoke!, producer, Jan Chapman]
  • A. Jan Chapman chosen
    Jan Chapman is an acclaimed Australian film producer known for her work on influential independent and art-house films.
  • B. Andrew Chapman
    Andrew Chapman is a television writer and producer best known for his work as an executive producer and showrunner on the medical drama series "The Resident."
  • C. Alan Strang
    Alan Strang is the troubled teenage protagonist of Peter Shaffer’s play "Equus," whose violent religious and sexual obsession with horses drives the drama’s psychological exploration.
  • D. Adam Chapman
    Adam Chapman is a television producer known for his work on the acclaimed nature documentary series "Our Planet."
  • E. Peter Chapman
    Peter Chapman is a writer and journalist known for his historical and political analyses of global corporations and their impact, including his work on the United Fruit Company.
  • 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_69d80766a21881909f21a1b7421d3b8a completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafa0ed508190b2855171b1945e84 completed April 12, 2026, 2:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75496496c819093a9e763d293bcf7 completed May 3, 2026, 1:58 p.m.
Created at: April 9, 2026, 9:44 p.m.