Triple

T14625484
Position Surface form Disambiguated ID Type / Status
Subject Mykelti Williamson E343332 entity
Predicate spouse P13 FINISHED
Object Sondra Spriggs E343332 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: Sondra Spriggs | Statement: [Mykelti Williamson, spouse, Sondra Spriggs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sondra Spriggs
Context triple: [Mykelti Williamson, spouse, Sondra Spriggs]
  • A. Sondra Spriggs chosen
    Sondra Spriggs is known as the former spouse of American actor Mykelti Williamson.
  • B. Melba Snyder
    Melba Snyder is a character associated with the animated television series "Zip."
  • C. Marilee Earle
    Marilee Earle is an actress best known for her role in the 1958 Western film "Terror in a Texas Town."
  • D. Darlene Snell
    Darlene Snell is a volatile and ruthless heroin producer and matriarch in the crime drama series "Ozark," known for her unpredictable violence and fierce protection of her land and legacy.
  • E. Betty Lou Bredemus
    Betty Lou Bredemus was an American acting coach and theater professional best known as the mother of actress Julia Roberts.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb46a4a9081908472b0a542028a7f completed April 14, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fedd1bb1c48190b5d2b4167c756abf completed May 9, 2026, 7:07 a.m.
Created at: April 10, 2026, 1:26 a.m.