Triple

T8995407
Position Surface form Disambiguated ID Type / Status
Subject Frieda Hughes E214893 entity
Predicate familyName P18 FINISHED
Object Hughes E119019 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: Hughes | Statement: [Frieda Hughes, familyName, Hughes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hughes
Context triple: [Frieda Hughes, familyName, Hughes]
  • A. Hughes chosen
    Hughes is a common English and Welsh surname of patronymic origin, derived from the given name Hugh.
  • B. Halleck
    Halleck is a surname most notably associated with American political and military figures, including U.S. Congressman Charles A. Halleck and Civil War general Henry Wager Halleck.
  • C. Langston
    Langston is the given name of Langston Hughes, the influential American poet, social activist, and central figure of the Harlem Renaissance.
  • D. Hillegas
    Hillegas is a surname most notably associated with Michael Hillegas, the first Treasurer of the United States.
  • E. Huges
    Huges is a variant spelling of the given name Hugues, commonly used in French-speaking contexts.
  • 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_69ca83a05c608190bdfdbdb25e994b39 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc68ddff288190869731df2c178ff6 completed April 1, 2026, 12:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0d0e6a08190a2faf4157b8a9cd4 completed April 3, 2026, 2:38 p.m.
Created at: March 30, 2026, 7:04 p.m.