Triple

T7781873
Position Surface form Disambiguated ID Type / Status
Subject Harcourt Williams E221539 entity
Predicate name P16 FINISHED
Object Harcourt Williams E221539 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: Harcourt Williams | Statement: [Harcourt Williams, name, Harcourt Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harcourt Williams
Context triple: [Harcourt Williams, name, Harcourt Williams]
  • A. Harcourt Williams chosen
    Harcourt Williams was a British actor and theatre director known for his work with the Old Vic and appearances in classic film adaptations of Shakespeare.
  • B. Randolph Clark
    Randolph Clark was an American educator and co-founder of Texas Christian University, instrumental in shaping higher education in Texas in the late 19th century.
  • C. William Fenwick Williams
    William Fenwick Williams was a British Army officer best known for his distinguished leadership and defense of the fortress city of Kars during the Crimean War.
  • D. Willis Herron
    Willis Herron was an American businessman best known for commissioning and building the iconic World’s Tallest Thermometer roadside attraction in Baker, California.
  • E. John H. Wilson
    John H. Wilson was a business partner in the Wilson Brothers & Company firm, likely involved in its management and commercial operations.
  • 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_69ca83ebbef881909ac47f789145fef7 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cadf1dcc6c8190b3c6ee4ff7808e02 completed March 30, 2026, 8:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69caf5d30c748190bbb71534cfdf4f75 completed March 30, 2026, 10:14 p.m.
Created at: March 30, 2026, 4:21 p.m.