Triple

T15293837
Position Surface form Disambiguated ID Type / Status
Subject Sadie McKee E365600 entity
Predicate editedBy P1954 FINISHED
Object Blanche Sewell E174755 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: Blanche Sewell | Statement: [Sadie McKee, editedBy, Blanche Sewell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blanche Sewell
Context triple: [Sadie McKee, editedBy, 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. Mary Bradham
    Mary Bradham is known as the daughter of Caleb Bradham, the pharmacist and inventor of Pepsi-Cola.
  • C. Mary Tayloe Lloyd
    Mary Tayloe Lloyd was an American woman from a prominent Maryland family best known as the wife of Francis Scott Key, author of the U.S. national anthem.
  • D. Elsie Wheeler
    Elsie Wheeler was the wife of Major Malcolm Wheeler-Nicholson, the pioneering American comic book publisher who founded the company that would become DC Comics.
  • E. Bessie Gilmore
    Bessie Gilmore was the mother of American criminal Gary Gilmore, whose life and family background drew public attention following his highly publicized execution in 1977.
  • 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_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03682ea488190ac82fdbd0e855d34 completed April 16, 2026, 1:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff01e2a03c81909ab24d4ed2b54698 completed May 9, 2026, 9:44 a.m.
Created at: April 10, 2026, 3:15 a.m.