Triple

T20884546
Position Surface form Disambiguated ID Type / Status
Subject Sir John Major E514241 entity
Predicate name P16 FINISHED
Object John Major 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: John Major | Statement: [Sir John Major, name, John Major]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Major
Context triple: [Sir John Major, name, John Major]
  • A. John Major chosen
    John Major is a British Conservative politician who served as Prime Minister of the United Kingdom from 1990 to 1997.
  • B. John C. Major
    John C. Major was a prominent figure significant enough in regional history or public life that Major County was named in his honor.
  • C. Edward Heath
    Edward Heath was a British Conservative politician who served as Prime Minister of the United Kingdom from 1970 to 1974 and led the country into the European Economic Community.
  • D. Tony Blair
    Tony Blair is a British politician who served as Prime Minister of the United Kingdom from 1997 to 2007 and was a leading architect of the UK’s intervention in the Iraq War.
  • E. Mark Thatcher
    Mark Thatcher is a British businessman and the son of former UK Prime Minister Margaret Thatcher, known for his controversial business dealings and involvement in political scandals.
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c67bd32c819097301e330e358c49 completed April 21, 2026, 12:36 a.m.
Created at: April 16, 2026, 12:46 p.m.