Triple

T10338792
Position Surface form Disambiguated ID Type / Status
Subject Evelyn Mulwray E243074 entity
Predicate hasRelative P367 FINISHED
Object Katherine E856906 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: Katherine | Statement: [Evelyn Mulwray, hasRelative, Katherine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katherine
Context triple: [Evelyn Mulwray, hasRelative, Katherine]
  • A. Katherine
    Katherine is a regional town in Australia's Northern Territory, known as a key service and transport hub near Nitmiluk (Katherine Gorge) National Park.
  • B. Katherine
    Katherine is one of the witty noblewomen in William Shakespeare’s comedy "Love’s Labour’s Lost," known for her sharp dialogue and role in the play’s romantic entanglements.
  • C. Katherine chosen
    Katherine is the daughter of Evelyn Mulwray in the 1974 film noir "Chinatown," whose parentage is central to the movie's mystery and emotional impact.
  • D. Kathryn
    Kathryn is a feminine given name, commonly considered a variant spelling of Katherine/Catherine.
  • E. Katherine Carey
    Katherine Carey was an English noblewoman of the late 16th century, a member of the influential Carey family closely connected to the Tudor court.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e0a470948190959f298dd6110bf3 completed April 7, 2026, 10:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69d79508427c81909db511e969bc9ddb completed April 9, 2026, 12:01 p.m.
Created at: April 6, 2026, 11:54 a.m.