Triple

T21413495
Position Surface form Disambiguated ID Type / Status
Subject The Shining Hour E528237 entity
Predicate editor P1954 FINISHED
Object Blanche Sewell 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: Blanche Sewell | Statement: [The Shining Hour, editor, Blanche Sewell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blanche Sewell
Context triple: [The Shining Hour, editor, Blanche Sewell]
  • A. Blanche Sewell chosen
    Blanche Sewell was an American film editor best known for her work on classic Hollywood productions, including the 1939 musical fantasy film "The Wizard of Oz."
  • B. Florence Gibbs
    Florence Gibbs was the first wife of American actor Tony Randall, to whom he was married for over 50 years until her death.
  • C. Mary Bradham
    Mary Bradham is known as the daughter of Caleb Bradham, the pharmacist and inventor of Pepsi-Cola.
  • D. Edna Spalding
    Edna Spalding is the resilient Depression-era widow at the center of the film "Places in the Heart," who struggles to save her Texas farm and family through courage and determination.
  • E. Mary Ella Wilkins
    Mary Ella Wilkins was an American author best known for her short stories and novels depicting New England village life, often published under the name Mary E. Wilkins Freeman.
  • 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_69e0c454c248819093425d1099101c09 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b201ce1481908392c77e5ca40f5f completed April 22, 2026, 11:33 a.m.
Created at: April 16, 2026, 5:44 p.m.