Triple

T8097379
Position Surface form Disambiguated ID Type / Status
Subject Dominic Cummings E189019 entity
Predicate advisorTo P488 FINISHED
Object Michael Gove E187669 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: Michael Gove | Statement: [Dominic Cummings, advisorTo, Michael Gove]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Gove
Context triple: [Dominic Cummings, advisorTo, Michael Gove]
  • A. Michael Gove chosen
    Michael Gove is a British Conservative politician who has held several senior government roles and was a prominent leader of the campaign for the United Kingdom to leave the European Union.
  • B. Liam Fox
    Liam Fox is a British Conservative politician and former Defence Secretary who has served as a Member of Parliament since 1992.
  • C. William Gove
    William Gove is the son of British Conservative politician Michael Gove.
  • D. Oliver Dowden
    Oliver Dowden is a British Conservative Party politician who has held several senior UK government roles, including serving in the Cabinet.
  • E. Chris Grayling
    Chris Grayling is a British Conservative politician and former cabinet minister who served in roles including Justice Secretary and Transport Secretary.
  • 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_69ca82b886d88190a9cba0d5a4a27521 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb429319048190b612c8060a9a24d2 completed March 31, 2026, 3:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccecf8f4a48190be0af148a9da4713 completed April 1, 2026, 10:01 a.m.
Created at: March 30, 2026, 5:30 p.m.