Triple

T15076434
Position Surface form Disambiguated ID Type / Status
Subject Charles Tennant E380012 entity
Predicate familyName P18 FINISHED
Object Tennant E363230 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: Tennant | Statement: [Charles Tennant, familyName, Tennant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tennant
Context triple: [Charles Tennant, familyName, Tennant]
  • A. Tennant chosen
    Tennant is a British surname borne by various notable figures in the arts, sciences, and public life.
  • B. Troughton
    Troughton is a British surname most notably associated with actor Patrick Troughton, who played the Second Doctor in the long-running television series Doctor Who.
  • C. Alex Tennant
    Alex Tennant is a fictional character on the television series "NCIS: Hawaiʻi," depicted as the teenage son of lead agent Jane Tennant.
  • D. Stockingford
    Stockingford is a residential suburb and former village within the town of Nuneaton in Warwickshire, England.
  • E. Whitrow
    Whitrow is an English surname most notably associated with the late British actor Benjamin Whitrow.
  • 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_69d85cd7683881908d405c1b5d7b4f7f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dff7fb60448190b454386dd762644d completed April 15, 2026, 8:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fea5d2765481908f101bef483ed02f completed May 9, 2026, 3:11 a.m.
Created at: April 10, 2026, 3:03 a.m.