Triple

T7798826
Position Surface form Disambiguated ID Type / Status
Subject Larry King E180370 entity
Predicate spouse P13 FINISHED
Object Freda Miller E180370 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: Freda Miller | Statement: [Larry King, spouse, Freda Miller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Freda Miller
Context triple: [Larry King, spouse, Freda Miller]
  • A. Freda Miller chosen
    Freda Miller is known primarily as the former spouse of American television and radio host Larry King.
  • B. Freda Wilson
    Freda Wilson was the wife of Irish physicist and Nobel laureate Ernest Walton.
  • C. Frieda Hughes
    Frieda Hughes is a British poet, painter, and writer, and the daughter of poets Sylvia Plath and Ted Hughes.
  • D. June Miller
    June Miller was an influential figure in the bohemian literary circles of early 20th-century New York and Paris, best known as the charismatic and complex muse of writer Henry Miller and a subject in Anaïs Nin’s diaries.
  • E. Constance Miller
    Constance Miller is the shrewd, opium-using madam who becomes a business partner and emotional counterpoint to John McCabe in Robert Altman’s revisionist Western film "McCabe & Mrs. Miller."
  • 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_69ca827d22208190b4dc5aa680edcf5d completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cae984185881908117f9f549ffc443 completed March 30, 2026, 9:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf883201d481909efd2f57e852a175 completed April 3, 2026, 9:28 a.m.
Created at: March 30, 2026, 4:32 p.m.