Triple

T21366231
Position Surface form Disambiguated ID Type / Status
Subject Barbara Cushing E526921 entity
Predicate familyName P18 FINISHED
Object Cushing 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: Cushing | Statement: [Barbara Cushing, familyName, Cushing]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cushing
Context triple: [Barbara Cushing, familyName, Cushing]
  • A. Cushing chosen
    Cushing is a surname most notably associated with American jurist and Squaw Valley Ski Resort founder Alexander Cushing, as well as a prominent New England family with historical influence in law and politics.
  • B. Battery Cushing
    Battery Cushing was a coastal artillery battery associated with Fort Andrews that formed part of the harbor defense system in the United States.
  • C. Burdinne
    Burdinne is a rural municipality in the province of Liège in Wallonia, Belgium, known for its agricultural landscape and small villages.
  • D. Kippel
    Kippel is a small Swiss mountain village and municipality in the canton of Valais, known for its traditional wooden houses and alpine scenery.
  • E. Coxen
    Coxen is a surname variant of Cox, typically of English origin.
  • 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_69e0b51d8a308190b09113b3b3f9bc15 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b06fbe108190a07a46824b96a963 completed April 22, 2026, 11:26 a.m.
Created at: April 16, 2026, 5:09 p.m.