Triple

T7135982
Position Surface form Disambiguated ID Type / Status
Subject A361 E166307 entity
Predicate connects P390 FINISHED
Object Devizes E334960 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: Devizes | Statement: [A361, connects, Devizes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Devizes
Context triple: [A361, connects, Devizes]
  • A. Devizes chosen
    Devizes is a historic market town and civil parish in Wiltshire, England, known for its medieval origins and well-preserved architecture.
  • B. Leintwardine
    Leintwardine is a small historic village in Herefordshire, England, near the Welsh border, known for its Roman heritage and rural setting.
  • C. Grosmont
    Grosmont is a small village in North Yorkshire, England, known for its heritage railway station on the North Yorkshire Moors Railway and its scenic moorland surroundings.
  • D. Brynmelin
    Brynmelin is a district within the City and County of Swansea in Wales, known primarily as a residential area of the city.
  • E. Drakeford
    Drakeford is a Welsh surname most prominently associated with Mark Drakeford, the former First Minister of Wales and leader of Welsh Labour.
  • 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_69c68884a9388190af42f90d1c1a7151 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e6926d748190bc8c150fc1860531 completed March 27, 2026, 8:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7a348a748819082f87039ea79f251 completed March 28, 2026, 9:45 a.m.
Created at: March 27, 2026, 2:45 p.m.