Triple

T16664920
Position Surface form Disambiguated ID Type / Status
Subject Maesteg School E404956 entity
Predicate inspectionAuthority P18396 FINISHED
Object Estyn E416351 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: Estyn | Statement: [Maesteg School, inspectionAuthority, Estyn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Estyn
Context triple: [Maesteg School, inspectionAuthority, Estyn]
  • A. Estyn chosen
    Estyn is the education and training inspectorate for Wales, responsible for evaluating the quality and standards of schools, colleges, and other learning providers.
  • B. Parea
    Parea is a small coastal village on the island of Huahine in French Polynesia, known for its tranquil beaches and traditional Polynesian atmosphere.
  • C. Yanda
    Yanda is a lesser-known Dogon language variety spoken by the Dogon people of Mali in West Africa.
  • D. Hwni
    Hwni is an alternative transliteration of Huni, an ancient Egyptian pharaoh of the Third Dynasty.
  • E. Tivissa
    Tivissa is a historic village in Catalonia, Spain, known for its scenic setting among the mountains of the Ribera d’Ebre region and its well-preserved medieval core.
  • 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_69d8838b5fbc81908c6575c132b82e80 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37c9be0688190afda306cde934c68 completed April 18, 2026, 12:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a008a32988c8190a671a4cbd829047a completed May 10, 2026, 1:37 p.m.
Created at: April 10, 2026, 5:18 a.m.