Triple

T21970956
Position Surface form Disambiguated ID Type / Status
Subject John and Mary E542585 entity
Predicate director P255 FINISHED
Object Peter Yates NE NERFINISHED

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: Peter Yates | Statement: [John and Mary, director, Peter Yates]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Yates
Context triple: [John and Mary, director, Peter Yates]
  • A. Peter Yates chosen
    Peter Yates was a British film director best known for stylish, character-driven works including the influential action thriller "Bullitt."
  • B. Michael Cimino
    Michael Cimino was an American film director and screenwriter best known for his ambitious, visually striking dramas and his Oscar-winning work on the Vietnam War epic "The Deer Hunter."
  • C. Michael Cimino
    Michael Cimino is an American actor best known for starring as Victor Salazar in the Hulu/Disney+ teen drama series "Love, Victor."
  • D. Joseph Schlamme
    Joseph Schlamme is the son of American actress and filmmaker Christine Lahti.
  • E. Alan J. Pakula
    Alan J. Pakula was an American film director, producer, and screenwriter best known for his politically charged thrillers and character-driven dramas of the 1970s and 1980s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c48070988190909db97667b9a0ac completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f12484b83081908c08e3285e0b14a9 completed April 28, 2026, 9:20 p.m.
Created at: April 16, 2026, 8:02 p.m.