Triple

T3861359
Position Surface form Disambiguated ID Type / Status
Subject Glamorgan E90143 entity
Predicate contains P35 FINISHED
Object Maesteg E86870 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: Maesteg | Statement: [Glamorgan, contains, Maesteg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maesteg
Context triple: [Glamorgan, contains, Maesteg]
  • A. Maesteg chosen
    Maesteg is a former coal-mining town in the Llynfi Valley of South Wales, known for its industrial heritage and close-knit community.
  • B. Ebbw Vale
    Ebbw Vale is a town in South Wales known for its industrial heritage, particularly in steelmaking and coal mining, and for serving as the main commercial and administrative hub of the surrounding area.
  • C. Brynmawr
    Brynmawr is a small town in South Wales known for its industrial heritage and position on the northern edge of the South Wales Valleys.
  • D. Cwmbran
    Cwmbran is a large new town in South Wales known for its extensive shopping centre and post-war planned development.
  • E. Brynglas
    Brynglas is a small rural halt and passing loop on the narrow-gauge Talyllyn Railway in Mid Wales.
  • 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_69aed95b3c088190a8f85d19e6070599 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec22a5dc8190be8298d1ce8ca449 completed March 9, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd7f58290881908c7622616a829c75 completed March 20, 2026, 5:09 p.m.
Created at: March 9, 2026, 3:19 p.m.