Triple

T21664299
Position Surface form Disambiguated ID Type / Status
Subject Ean Evans E534669 entity
Predicate givenName P17 FINISHED
Object Ean 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: Ean | Statement: [Ean Evans, givenName, Ean]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ean
Context triple: [Ean Evans, givenName, Ean]
  • A. Ean chosen
    Ean is a given name, typically considered a variant of Ian or John, used primarily in English-speaking contexts.
  • B. Maa
    Maa is a Nilotic language spoken primarily by the Maasai people of Kenya and Tanzania.
  • C. Maa
    Maa is a revered Hindu mother goddess, often worshipped in her fierce and protective form as Sherawali, the lion-riding deity.
  • D. Estyn
    Estyn is the education and training inspectorate for Wales, responsible for evaluating the quality and standards of schools, colleges, and other learning providers.
  • E. Mainas
    Mainas is an alternative name for the Maynas, an Indigenous people historically inhabiting parts of the Amazon basin in present-day Peru and neighboring regions.
  • 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_69e0c467e1f48190af2650b19175abc4 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef6c0a2a58819086db5b5c1c0f3371 completed April 27, 2026, 2 p.m.
Created at: April 16, 2026, 6:36 p.m.