Triple

T21991876
Position Surface form Disambiguated ID Type / Status
Subject One Day E543108 entity
Predicate castMember P1668 FINISHED
Object Romola Garai 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: Romola Garai | Statement: [One Day, castMember, Romola Garai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Romola Garai
Context triple: [One Day, castMember, Romola Garai]
  • A. Romola Garai chosen
    Romola Garai is an English actress known for her performances in period dramas and literary adaptations in film and television.
  • B. Pamela Rabe
    Pamela Rabe is an acclaimed Canadian-Australian actress and theatre director known for her powerful stage work and prominent roles in Australian film and television.
  • C. Laura Penn
    Laura Penn is known as the spouse of American screenwriter and director Zak Penn.
  • D. Miranda Raison
    Miranda Raison is an English actress known for her work in television, film, and theatre, including roles in "Spooks," "Doctor Who," and various stage productions.
  • E. Margot Tennant
    Margot Tennant, later Margot Asquith, was a prominent British socialite, author, and wit who became the influential second wife of Prime Minister H. H. Asquith.
  • 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_69e0c48136b081908831fa907cc02e18 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1270e951081908deda039b47ca84b completed April 28, 2026, 9:30 p.m.
Created at: April 16, 2026, 8:05 p.m.