Triple

T22802497
Position Surface form Disambiguated ID Type / Status
Subject Beach Red E564434 entity
Predicate starring P1507 FINISHED
Object Geneviève Bujold 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: Geneviève Bujold | Statement: [Beach Red, starring, Geneviève Bujold]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geneviève Bujold
Context triple: [Beach Red, starring, Geneviève Bujold]
  • A. Geneviève Bujold chosen
    Geneviève Bujold is a Canadian actress acclaimed for her intense, intelligent performances in films such as "Anne of the Thousand Days" and numerous international productions.
  • B. Lois McMaster Bujold
    Lois McMaster Bujold is an acclaimed American science fiction and fantasy author best known for her Vorkosigan Saga and multiple Hugo and Nebula Award–winning novels.
  • C. Sandra Henderson
    Sandra Henderson is a Canadian former athlete best known for co-lighting the Olympic cauldron at the 1976 Summer Olympics in Montreal.
  • D. Ed McCaffrey
    Ed McCaffrey is a former NFL wide receiver, best known for his time with the Denver Broncos, with whom he won multiple Super Bowls.
  • E. Diana Gabaldon
    Diana Gabaldon is an American author best known for writing the historical time-travel romance series "Outlander," which inspired the popular television adaptation.
  • 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_69e245823f4c8190ade442cdcc2c224a completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17cdf1e308190a05d0f61856be544 completed April 29, 2026, 3:37 a.m.
Created at: April 17, 2026, 3:31 p.m.