Triple

T19396705
Position Surface form Disambiguated ID Type / Status
Subject Don Laws E485208 entity
Predicate knownAs P39 FINISHED
Object Don Laws 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: Don Laws | Statement: [Don Laws, knownAs, Don Laws]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Don Laws
Context triple: [Don Laws, knownAs, Don Laws]
  • A. Don Laws chosen
    Don Laws was a prominent American figure skating coach and former competitive skater, best known for mentoring elite athletes and contributing significantly to the sport’s development.
  • B. Don Law
    Don Law was a prominent record producer best known for his influential work in country and early rock music, including classic recordings by artists like Johnny Cash and Marty Robbins.
  • C. Dennis Lipscomb
    Dennis Lipscomb was an American character actor known for his work in film and television from the late 1970s through the 1990s, often appearing in dramas and thrillers.
  • D. George McGinnis
    George McGinnis is a Hall of Fame American basketball forward known for his dominant scoring and rebounding in the ABA and NBA during the 1970s, particularly with the Indiana Pacers and Philadelphia 76ers.
  • E. Don D. Scott
    Don D. Scott is an American screenwriter best known for writing the hit comedy film "Barbershop" and its sequel.
  • 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_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62573f5788190a635b92121db2cf7 completed April 20, 2026, 1:09 p.m.
Created at: April 10, 2026, 1:36 p.m.