Triple

T19184383
Position Surface form Disambiguated ID Type / Status
Subject Thomas Vereker E469661 entity
Predicate familyName P18 FINISHED
Object Vereker 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: Vereker | Statement: [Thomas Vereker, familyName, Vereker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vereker
Context triple: [Thomas Vereker, familyName, Vereker]
  • A. Vereker chosen
    Vereker is an Anglo-Irish noble family name historically associated with the Viscounts Gort and other members of the British and Irish aristocracy.
  • B. Vere
    Vere is the given name of Vere Gordon Childe, a prominent Australian archaeologist known for his influential theories on prehistoric societies and social evolution.
  • C. Verey
    Verey is an English surname most notably associated with renowned garden designer and writer Rosemary Verey.
  • D. Keverich
    Keverich is a German surname historically associated with Maria Magdalena Keverich, the mother of composer Ludwig van Beethoven.
  • E. Verchota
    Verchota is a surname most notably associated with Phil Verchota, an American ice hockey player and member of the 1980 "Miracle on Ice" U.S. Olympic team.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f61f1d9c8190b67555383d821958 completed April 20, 2026, 9:47 a.m.
Created at: April 10, 2026, 12:07 p.m.