Triple

T1801404
Position Surface form Disambiguated ID Type / Status
Subject Press for Time E39725 entity
Predicate hasCastMember P2308 FINISHED
Object Frances White E202332 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: Frances White | Statement: [Press for Time, hasCastMember, Frances White]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frances White
Context triple: [Press for Time, hasCastMember, Frances White]
  • A. Frances White chosen
    Frances White is a British actress known for her work in film, television, and theatre, including a role in the Norman Wisdom comedy "Press for Time."
  • B. Verna Felton
    Verna Felton was an American character actress and voice performer best known for her memorable roles in classic Disney animated films.
  • C. Betty Irene Whitaker
    Betty Irene Whitaker is the wife of Intel co-founder and philanthropist Gordon E. Moore and a partner in his philanthropic endeavors.
  • D. Mary Holden
    Mary Holden is a character portrayed by Judy Garland in the 1940 MGM musical film "Strike Up the Band."
  • E. Bernice Layne Brown
    Bernice Layne Brown was the mother of California governor Jerry Brown and a prominent figure in California political and civic life.
  • 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_69a88632aa588190ba3978fde0db5bbd completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa656ad5d4819090e677ad137b0cd1 completed March 6, 2026, 5:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69adc9a799fc81909acb620f3e569265 completed March 8, 2026, 7:10 p.m.
Created at: March 4, 2026, 7:32 p.m.