Triple

T5181620
Position Surface form Disambiguated ID Type / Status
Subject 1987 United Kingdom general election E116933 entity
Predicate seatChangeConservative P20306 FINISHED
Object -21 LITERAL 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: -21 | Statement: [1987 United Kingdom general election, seatChangeConservative, -21]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: seatChangeConservative
Context triple: [1987 United Kingdom general election, seatChangeConservative, -21]
  • A. ConservativeSeatChange chosen
    Indicates the change in the number of seats held by the Conservative party between two electoral periods.
  • B. ConservativeSeatsWon
    Indicates the number of parliamentary or legislative seats won by the Conservative party in an election.
  • C. LabourSeatChange
    Indicates a change in the number of parliamentary seats held by the Labour Party between two electoral outcomes.
  • D. numberOfVotesConservative
    Indicates the number of votes that were cast for the Conservative option or party in a given context.
  • E. LiberalSeatChange
    Indicates a change in the number of seats held by the Liberal party between two points in time.
  • F. None of above.

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_69bd446140f08190becb93c61158f27f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd799bc58c819098a8e91e21baaef4 completed March 20, 2026, 4:45 p.m.
PD Predicate disambiguation batch_69bd77b529948190b86671ebe43f4734 completed March 20, 2026, 4:37 p.m.
Created at: March 20, 2026, 1:45 p.m.