Triple

T14571700
Position Surface form Disambiguated ID Type / Status
Subject Harlem, Georgia E341930 entity
Predicate birthplaceOf P1 FINISHED
Object Oliver Hardy E176932 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: Oliver Hardy | Statement: [Harlem, Georgia, birthplaceOf, Oliver Hardy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oliver Hardy
Context triple: [Harlem, Georgia, birthplaceOf, Oliver Hardy]
  • A. Oliver Hardy chosen
    Oliver Hardy was an American comic actor best known as one half of the legendary film comedy duo Laurel and Hardy.
  • B. Stan Laurel
    Stan Laurel was a British-born comic actor, writer, and director best known as one half of the legendary slapstick duo Laurel and Hardy.
  • C. Charley Chase
    Charley Chase was an American silent and early sound film comedian, actor, and director best known for his work in short comedies at the Hal Roach Studios in the 1920s and 1930s.
  • D. W. C. Fields
    W. C. Fields was a famed American comedian, actor, and writer known for his misanthropic persona, distinctive drawl, and influential work in vaudeville and early Hollywood films.
  • E. Bud Abbott
    Bud Abbott was an American comedian and straight man best known as one half of the legendary comedy duo Abbott and Costello.
  • 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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb3f33b1c8190bb447788bfd28d51 completed April 14, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8aca591081908db149ec517a999b completed May 8, 2026, 7:03 a.m.
Created at: April 10, 2026, 1:23 a.m.