Triple

T15698487
Position Surface form Disambiguated ID Type / Status
Subject Frances (1982 film) E380530 entity
Predicate director P255 FINISHED
Object Graeme Clifford E879852 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: Graeme Clifford | Statement: [Frances (1982 film), director, Graeme Clifford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Graeme Clifford
Context triple: [Frances (1982 film), director, Graeme Clifford]
  • A. Graeme Clifford chosen
    Graeme Clifford is an Australian film editor and director known for his work on influential films of the 1970s and 1980s.
  • B. Graeme Revell
    Graeme Revell is a New Zealand-born composer best known for his atmospheric film scores across genres including horror, action, and science fiction.
  • C. Graeme McDonald
    Graeme McDonald is a television producer known for his work on the British series "Meantime."
  • D. Graeme Gibson
    Graeme Gibson was a Canadian novelist, environmentalist, and cultural advocate known for his contributions to Canadian literature and his long partnership with writer Margaret Atwood.
  • E. Graeme Ferguson
    Graeme Ferguson was a Canadian filmmaker and co-founder of the IMAX large-format cinema technology.
  • 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_69d86d99e860819094b6957cde470f2c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f6c3328819081325b702ca92862 completed April 16, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0025e9b00c81908cb5f305c894363f completed May 10, 2026, 6:30 a.m.
Created at: April 10, 2026, 4:44 a.m.