Triple

T7077286
Position Surface form Disambiguated ID Type / Status
Subject Lord Judge E164850 entity
Predicate succeededBy P78 FINISHED
Object Lord Thomas of Cwmgiedd E501671 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: Lord Thomas of Cwmgiedd | Statement: [Lord Judge, succeededBy, Lord Thomas of Cwmgiedd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lord Thomas of Cwmgiedd
Context triple: [Lord Judge, succeededBy, Lord Thomas of Cwmgiedd]
  • A. Lord Thomas of Cwmgiedd chosen
    Lord Thomas of Cwmgiedd is a British judge who served as Lord Chief Justice of England and Wales from 2013 to 2017.
  • B. Sir Rhys Davies
    Sir Rhys Davies was a distinguished Welsh Labour politician and long-serving Member of Parliament noted for his advocacy of workers’ rights and social reform in the early to mid-20th century.
  • C. Sir Wyn Williams
    Sir Wyn Williams is a Welsh judge who has served as President of Welsh Tribunals and previously as a High Court judge of England and Wales.
  • D. Sir Ifor Williams
    Sir Ifor Williams was a prominent Welsh scholar and philologist renowned for his pioneering work on early Welsh literature and poetry.
  • E. Sir Thomas Fitz
    Sir Thomas Fitz was an architect known for designing the historic Windsor Guildhall in Windsor, England.
  • 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_69c6887cbc6c8190bdfac42d940f4d8a completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e4ee29288190a9a3fa7a6c713d8f completed March 27, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7946dbf048190a6307fefeb1dd6a9 completed March 28, 2026, 8:42 a.m.
Created at: March 27, 2026, 2:40 p.m.