Triple

T19534499
Position Surface form Disambiguated ID Type / Status
Subject Hayley Williams E488734 entity
Predicate givenName P17 FINISHED
Object Hayley 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: Hayley | Statement: [Hayley Williams, givenName, Hayley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hayley
Context triple: [Hayley Williams, givenName, Hayley]
  • A. Hayley
    Hayley is a Canadian former ice hockey player widely regarded as one of the greatest female hockey players of all time.
  • B. Hayley chosen
    Hayley is a feminine given name commonly used in English-speaking countries, often associated with meanings related to hay meadows or clearings.
  • C. Hayley Green
    Hayley Green is a small residential area within the civil parish of Warfield in Berkshire, England.
  • D. Hayley Haller
    Hayley Haller is a fictional character in Michael Connelly’s Lincoln Lawyer series, known as the teenage daughter of defense attorney Mickey Haller.
  • E. Hayley Squires
    Hayley Squires is an English actress and writer known for her acclaimed performances in film, television, and theatre, including her breakout role in Ken Loach's "I, Daniel Blake."
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e636417ed88190b4c66a323bca776f completed April 20, 2026, 2:20 p.m.
Created at: April 10, 2026, 1:41 p.m.