Triple

T5348716
Position Surface form Disambiguated ID Type / Status
Subject Alexander Woollcott E124118 entity
Predicate familyName P18 FINISHED
Object Woollcott E124118 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: Woollcott | Statement: [Alexander Woollcott, familyName, Woollcott]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Woollcott
Context triple: [Alexander Woollcott, familyName, Woollcott]
  • A. Robert Benchley
    Robert Benchley was an American humorist, writer, and actor best known for his witty essays, film shorts, and membership in the Algonquin Round Table.
  • B. Alexander Woollcott chosen
    Alexander Woollcott was an American critic, commentator, and member of the Algonquin Round Table, known for his sharp wit and influential work in theater and radio.
  • C. Grover Wolfe
    Grover Wolfe was the older brother of American novelist Thomas Wolfe, remembered primarily through his connection to the writer’s life and family background.
  • D. Harry Crosby
    Harry Crosby is an American investment banker and philanthropist, best known as one of the sons of legendary singer and actor Bing Crosby.
  • E. Irvin S. Cobb
    Irvin S. Cobb was an American humorist, author, and journalist known for his witty short stories, columns, and contributions to early 20th-century newspapers and magazines.
  • 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_69bd464be27081908807b40b75c1bbae completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd860ea7088190ad7be14132927d17 completed March 20, 2026, 5:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf21d0d4d08190a33c86553d2012fa completed March 21, 2026, 10:55 p.m.
Created at: March 20, 2026, 2:01 p.m.