Triple

T3673081
Position Surface form Disambiguated ID Type / Status
Subject Kingpin E77923 entity
Predicate cinematographer P1953 FINISHED
Object Mark Irwin E375228 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: Mark Irwin | Statement: [Kingpin, cinematographer, Mark Irwin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Irwin
Context triple: [Kingpin, cinematographer, Mark Irwin]
  • A. Mark Irwin chosen
    Mark Irwin is a Canadian cinematographer known for his work on numerous feature films, including collaborations with directors like David Cronenberg and on popular comedies such as "Old School."
  • B. John Irwin
    John Irwin is a television producer best known for his work as an executive producer on major late-night talk shows, including The Jay Leno Show.
  • C. Ken Moffett
    Ken Moffett was a prominent American labor mediator and union negotiator best known for his key role in resolving major sports labor disputes, including those in Major League Baseball.
  • D. Ken Hutchison
    Ken Hutchison was a Scottish actor known for his intense character roles in film and television during the 1970s and 1980s.
  • E. Alan Osbiston
    Alan Osbiston was a British film editor known for his work on notable mid-20th-century films, including major war and drama productions.
  • 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_69ad85e083008190b2e1b7085fe500bd completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc42f82548190b4d5f0fe7250decb completed March 8, 2026, 6:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b48854a2308190ba6a9fc39929b35c completed March 13, 2026, 9:57 p.m.
Created at: March 8, 2026, 3:25 p.m.