Triple

T4524991
Position Surface form Disambiguated ID Type / Status
Subject Arlene Foster E103354 entity
Predicate twitterUsername P2943 FINISHED
Object ArleneFosterUK E103354 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: ArleneFosterUK | Statement: [Arlene Foster, twitterUsername, ArleneFosterUK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ArleneFosterUK
Context triple: [Arlene Foster, twitterUsername, ArleneFosterUK]
  • A. Mary Lou McDonald
    Mary Lou McDonald is an Irish politician who leads Sinn Féin and has been a prominent figure in contemporary Irish republican and left-wing politics.
  • B. Arlene Foster chosen
    Arlene Foster is a Northern Irish politician who served as leader of the Democratic Unionist Party and as First Minister of Northern Ireland.
  • C. Moira Buffini
    Moira Buffini is a British playwright and screenwriter known for works such as the film adaptation of "Jane Eyre" and the play "Dinner."
  • D. Nicky Morgan
    Nicky Morgan is a British Conservative politician who served as Secretary of State for Education and later as Secretary of State for Digital, Culture, Media and Sport.
  • E. Christine Angus
    Christine Angus was the wife of British painter Walter Sickert, associated with his personal life during his early 20th-century career.
  • 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_69bd43dba59881908cf59b31df8c7ae1 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd577490f48190ac1fb3cbf3d8a41e completed March 20, 2026, 2:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69bda4483aa481909a100bf20085d667 completed March 20, 2026, 7:47 p.m.
Created at: March 20, 2026, 1:03 p.m.