Triple

T4981594
Position Surface form Disambiguated ID Type / Status
Subject River Afan E111897 entity
Predicate flowsThrough P225 FINISHED
Object Aberavon E301572 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: Aberavon | Statement: [River Afan, flowsThrough, Aberavon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aberavon
Context triple: [River Afan, flowsThrough, Aberavon]
  • A. Aberavon chosen
    Aberavon is a parliamentary constituency in South Wales that historically elected Labour MPs, including future Prime Minister Ramsay MacDonald.
  • B. Keynsham
    Keynsham is a town in Somerset, England, situated between Bristol and Bath and known for its historic market-town character and riverside setting.
  • C. Blaenymaes
    Blaenymaes is a residential area and housing estate located within the City and County of Swansea in South Wales.
  • D. Bridgend
    Bridgend is a small village on the Scottish island of Islay, known for its rural setting and role as a local hub near the island’s central crossroads.
  • E. Bridgend
    Bridgend is a town and county borough in South Wales, situated roughly midway between Cardiff and Swansea and known historically for its market and industrial heritage.
  • 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_69bd441adc208190b70a033a0741d01e completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd725310088190a44b5c02658edc52 completed March 20, 2026, 4:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69be8a0f90048190998dad99555891c0 completed March 21, 2026, 12:07 p.m.
Created at: March 20, 2026, 1:33 p.m.