Triple

T21326479
Position Surface form Disambiguated ID Type / Status
Subject Harlan Howard E525770 entity
Predicate spouse P13 FINISHED
Object Jan Howard 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: Jan Howard | Statement: [Harlan Howard, spouse, Jan Howard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jan Howard
Context triple: [Harlan Howard, spouse, Jan Howard]
  • A. Jan Howard chosen
    Jan Howard was an American country music singer and Grand Ole Opry star known for hits like "Evil on Your Mind" and her collaborations with Bill Anderson.
  • B. Marilyn Howard
    Marilyn Howard is the daughter of Curly Howard, the famed member of the comedy trio The Three Stooges.
  • C. Patti Woodward
    Patti Woodward is known as the former wife of American television news producer Don Hewitt, the creator of the CBS program "60 Minutes."
  • D. Shirley Owens
    Shirley Owens is an American singer best known as the lead vocalist of the girl group The Shirelles, pioneers of the early 1960s pop and R&B sound.
  • E. Glenda Parks
    Glenda Parks is the central protagonist of the romantic comedy film "Seems Like Old Times," around whom the story’s comedic and romantic entanglements revolve.
  • 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_69e0b51b90788190a4dd823d962626da completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7ab49aa48819083b3793657903216 completed April 21, 2026, 4:52 p.m.
Created at: April 16, 2026, 4:41 p.m.