Triple

T12146431
Position Surface form Disambiguated ID Type / Status
Subject Polly Bergen E289333 entity
Predicate spouse P13 FINISHED
Object Freddie Fields E673151 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: Freddie Fields | Statement: [Polly Bergen, spouse, Freddie Fields]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Freddie Fields
Context triple: [Polly Bergen, spouse, Freddie Fields]
  • A. Freddie Fields chosen
    Freddie Fields was an American film producer and talent agent known for his influential role in Hollywood and involvement in acclaimed films such as "Glory."
  • B. Freddie Young
    Freddie Young was a renowned British cinematographer best known for his sweeping, visually stunning work on epic films such as "Lawrence of Arabia."
  • C. Freddie Taylor
    Freddie Taylor is the central protagonist of the British coming-of-age film "Cemetery Junction," a young man struggling to escape his small-town life and find a more meaningful future.
  • D. Freddie Lyon
    Freddie Lyon is a driven and idealistic investigative journalist in the British television drama series "The Hour," known for his sharp intellect and uncompromising pursuit of the truth.
  • E. Freddie Bullivant
    Freddie Bullivant is the central character of the show "Fixing it for Freddie," around whom the series’ stories and events revolve.
  • 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_69d6ab4c6710819097a9d228382dde43 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915ac2ebc81909155f9b2fb4a2252 completed April 10, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f696ec648190aa43655ac8a2b312 completed May 2, 2026, 1:05 p.m.
Created at: April 8, 2026, 9:49 p.m.