Triple

T15683410
Position Surface form Disambiguated ID Type / Status
Subject John Tovey E377635 entity
Predicate familyName P18 FINISHED
Object Tovey E334255 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: Tovey | Statement: [John Tovey, familyName, Tovey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tovey
Context triple: [John Tovey, familyName, Tovey]
  • A. Tovey chosen
    Tovey is an English surname most notably associated with actor Russell Tovey, known for his work in British television, film, and theatre.
  • B. John Tovey
    John Tovey is a notable individual distinguished by his association with the surname Tovey, recognized for his contributions in his respective field.
  • C. Alsop
    Alsop is an English-language surname borne by various notable individuals across fields such as music, journalism, and politics.
  • D. Clementi
    Clementi is a residential town and planning area in the western region of Singapore, known for its housing estates, schools, and transport links.
  • E. Tippett
    Tippett is a surname most notably associated with Phil Tippett, the acclaimed visual effects supervisor and stop-motion animator known for his work on films like Star Wars and Jurassic Park.
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f31b5b881908e46ecd9fc6048ab completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6ee4c8688190ae2fefb56171161a completed May 9, 2026, 5:29 p.m.
Created at: April 10, 2026, 4:17 a.m.