Triple

T22101341
Position Surface form Disambiguated ID Type / Status
Subject Saraband for Dead Lovers E546177 entity
Predicate castMember P1668 FINISHED
Object Flora Robson 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: Flora Robson | Statement: [Saraband for Dead Lovers, castMember, Flora Robson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Flora Robson
Context triple: [Saraband for Dead Lovers, castMember, Flora Robson]
  • A. Flora Robson chosen
    Flora Robson was a distinguished British actress known for her powerful character roles in both stage and film, often portraying strong, authoritative women.
  • B. Celia Johnson
    Celia Johnson was a distinguished English actress best known for her nuanced, understated performances in classic British films such as "Brief Encounter."
  • C. Helen Christie
    Helen Christie was a British actress known for her work in mid-20th-century film, television, and theatre.
  • D. Polly Benedict
    Polly Benedict is a recurring love interest of the title character in the classic "Andy Hardy" film series.
  • E. Phyllis Fraser
    Phyllis Fraser was an American actress-turned-publishing executive and children's book editor who co-founded Beginner Books and played a key role in popularizing early readers like those by Dr. Seuss.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1291501508190ad5689be5abb2ba6 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.