Triple

T20287979
Position Surface form Disambiguated ID Type / Status
Subject Vale of Neath E509939 entity
Predicate contains P35 FINISHED
Object Crynant 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: Crynant | Statement: [Vale of Neath, contains, Crynant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Crynant
Context triple: [Vale of Neath, contains, Crynant]
  • A. Crynant chosen
    Crynant is a small village and community in the Dulais Valley of Neath Port Talbot, South Wales, historically associated with coal mining.
  • B. Talygarn
    Talygarn is a village and residential area in Rhondda Cynon Taf, Wales, known for its historic estate and former rehabilitation hospital.
  • C. Gryneion
    Gryneion was an ancient Greek coastal city of Aeolis in western Asia Minor, known from classical sources as a minor but historically attested settlement.
  • D. Crithoni
    Crithoni is an ancient coastal settlement located on Alinda Bay in the region of Caria, in what is now southwestern Turkey.
  • E. Dryna
    Dryna is an island located within the municipality of Haram in Møre og Romsdal county, Norway.
  • 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6769414488190b38e07fd1e989aba completed April 20, 2026, 6:55 p.m.
Created at: April 16, 2026, 11:09 a.m.