Triple

T11482448
Position Surface form Disambiguated ID Type / Status
Subject Romero E272185 entity
Predicate director P255 FINISHED
Object John Duigan E918559 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: John Duigan | Statement: [Romero, director, John Duigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Duigan
Context triple: [Romero, director, John Duigan]
  • A. John Duigan chosen
    John Duigan is an Australian film director and screenwriter known for character-driven dramas such as "The Year My Voice Broke" and "Sirens."
  • B. Arthur Dignam
    Arthur Dignam was an Australian actor known for his distinctive character roles in film, television, and theatre.
  • C. Philip McKeon
    Philip McKeon was an American actor best known for playing Tommy Hyatt, the son of the title character, on the sitcom "Alice."
  • D. John McEwan
    John McEwan is a relatively obscure individual whose primary distinguishing feature is sharing the McEwan surname rather than broad public recognition.
  • E. John Cahill
    John Cahill is a name shared by several notable individuals, including figures in politics, law, and sports.
  • 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_69d6aae1b09881909ce2ded3fa0c14fa completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d85a1d86b88190b180f6b0d0a27029 completed April 10, 2026, 2:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69e624b12c04819085cc5f7dd64283ca completed April 20, 2026, 1:05 p.m.
Created at: April 8, 2026, 9:36 p.m.