Triple

T19301013
Position Surface form Disambiguated ID Type / Status
Subject Edwin Horne E482693 entity
Predicate child P120 FINISHED
Object Lena Horne 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: Lena Horne | Statement: [Edwin Horne, child, Lena Horne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lena Horne
Context triple: [Edwin Horne, child, Lena Horne]
  • A. Lena Horne chosen
    Lena Horne was an acclaimed American singer, actress, and civil rights activist renowned for her work in jazz and popular music as well as her groundbreaking roles in film and television.
  • B. Lorraine Hines
    Lorraine Hines is known as the former spouse of British actor Frazer Hines, who is best recognized for his role in the classic television series "Doctor Who."
  • C. Pearl Bailey
    Pearl Bailey was an acclaimed American singer and actress known for her charismatic stage presence and Tony Award–winning performance in the all-Black Broadway production of "Hello, Dolly!".
  • D. Virginia Bell Horne
    Virginia Bell Horne was the wife of American film and television actor Lloyd Nolan.
  • E. Eva Dandridge
    Eva Dandridge is the strict, no-nonsense older sister whose controlling nature over her siblings’ lives drives the romantic conflict and comedy in the film "Deliver Us from Eva."
  • 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_69d8e8d04d5c8190baa816986f2b1d1e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fc8a2a5c8190bfe95e40d3c93a42 completed April 20, 2026, 10:14 a.m.
Created at: April 10, 2026, 1:31 p.m.