Triple

T18819619
Position Surface form Disambiguated ID Type / Status
Subject Rafferty Law E460227 entity
Predicate hasHalfSibling P54212 FINISHED
Object Sophia Law 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: Sophia Law | Statement: [Rafferty Law, hasHalfSibling, Sophia Law]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sophia Law
Context triple: [Rafferty Law, hasHalfSibling, Sophia Law]
  • A. Sophia Law chosen
    Sophia Law is a British celebrity child known as one of actor Jude Law’s daughters.
  • B. Maggie Law
    Maggie Law is a member of the Law family, related to British model and actor Rafferty Law and connected to the wider circle of the actor Jude Law’s relatives.
  • C. Pauline Yeung
    Pauline Yeung is a Hong Kong actress and former beauty queen best known for her film and television roles in the late 1980s and early 1990s.
  • D. Pauline Wong
    Pauline Wong is a Hong Kong actress best known for her roles in 1980s supernatural and horror-comedy films, particularly in the Mr. Vampire series.
  • E. Regina Fong
    Regina Fong was the drag persona of British performer Reginald Sutherland Bundy, known for her camp cabaret acts and cult following on the London gay scene in the 1980s and 1990s.
  • 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a6b8b7d88190a8828746176776ea completed April 20, 2026, 4:08 a.m.
Created at: April 10, 2026, 11:55 a.m.