Triple

T4490075
Position Surface form Disambiguated ID Type / Status
Subject Frank Alfred Odysseus Johnson E107348 entity
Predicate father P120 FINISHED
Object Boris Johnson E11940 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: Boris Johnson | Statement: [Frank Alfred Odysseus Johnson, father, Boris Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Boris Johnson
Context triple: [Frank Alfred Odysseus Johnson, father, Boris Johnson]
  • A. Boris Johnson chosen
    Boris Johnson is a British Conservative politician who served as Prime Minister of the United Kingdom from 2019 to 2022 and was a leading figure in the Brexit campaign.
  • B. Rishi Sunak
    Rishi Sunak is a British politician who has served as Prime Minister of the United Kingdom and leader of the Conservative Party.
  • C. William Rutlish
    William Rutlish was a 17th-century embroiderer to the English royal court and benefactor whose legacy in education is commemorated by Rutlish School bearing his name.
  • D. Keir Starmer
    Keir Starmer is a British politician and former human rights lawyer who leads the Labour Party and serves as the United Kingdom’s Leader of the Opposition.
  • E. Theresa May
    Theresa May is a British politician who served as Prime Minister of the United Kingdom from 2016 to 2019.
  • 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_69bd43f84f788190a1383579c4a595be completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd556d29f08190bab1e872dd7e819f completed March 20, 2026, 2:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd67aee5908190888efb94eee725e5 completed March 20, 2026, 3:28 p.m.
Created at: March 20, 2026, 12:59 p.m.