Triple

T11758283
Position Surface form Disambiguated ID Type / Status
Subject Penglais campus E279586 entity
Predicate locatedIn P40 FINISHED
Object Aberystwyth E37121 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: Aberystwyth | Statement: [Penglais campus, locatedIn, Aberystwyth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aberystwyth
Context triple: [Penglais campus, locatedIn, Aberystwyth]
  • A. Aberystwyth chosen
    Aberystwyth is a historic seaside and university town on the west coast of Wales, known for its promenade, castle ruins, and role as a cultural and administrative center for the region.
  • B. Haverfordwest
    Haverfordwest is a historic market town in southwest Wales that serves as the principal commercial and administrative centre of Pembrokeshire.
  • C. Carmarthen
    Carmarthen is a historic market town in southwest Wales, often regarded as one of the oldest towns in the country and traditionally linked with the legends of Merlin.
  • D. Machynlleth
    Machynlleth is a historic market town in mid Wales, known for its role as the seat of Owain Glyndŵr’s Welsh Parliament and its strong cultural and environmental focus.
  • E. Penryn
    Penryn is a historic town and former parliamentary borough in Cornwall, England.
  • 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_69d6ab01038c819080714901502c84fc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a5220f148190ae60d1941a579ab6 completed April 10, 2026, 7:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69f4174972ac819094f3938b18a5081e completed May 1, 2026, 3 a.m.
Created at: April 8, 2026, 9:41 p.m.