Triple

T19147768
Position Surface form Disambiguated ID Type / Status
Subject Ouida Bergère E468724 entity
Predicate partnerInProfession P94073 FINISHED
Object George Fitzmaurice 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: George Fitzmaurice | Statement: [Ouida Bergère, partnerInProfession, George Fitzmaurice]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Fitzmaurice
Context triple: [Ouida Bergère, partnerInProfession, George Fitzmaurice]
  • A. George Fitzmaurice chosen
    George Fitzmaurice was an Irish-American film director best known for his work during the silent and early sound eras of Hollywood cinema.
  • B. Charles Fitzpatrick
    Charles Fitzpatrick was a Canadian lawyer, judge, and politician who served as Chief Justice of Canada and played a prominent role in federal politics in the late 19th and early 20th centuries.
  • C. George William Hamilton
    George William Hamilton was the son of American actor George Hamilton.
  • D. William Stewart
    William Stewart was an individual significant enough in regional history or exploration that the Stewart River in Canada was named in his honor.
  • E. Richard Francis-Bruce
    Richard Francis-Bruce is an Australian film editor renowned for his work on major Hollywood action and drama films.
  • 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e97a79a48190b243553023bf9081 completed April 20, 2026, 8:53 a.m.
Created at: April 10, 2026, 12:06 p.m.