Triple

T21312499
Position Surface form Disambiguated ID Type / Status
Subject Wanlockhead E525377 entity
Predicate postalTown P2711 FINISHED
Object Sanquhar 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: Sanquhar | Statement: [Wanlockhead, postalTown, Sanquhar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanquhar
Context triple: [Wanlockhead, postalTown, Sanquhar]
  • A. Sanquhar chosen
    Sanquhar is a small historic town in southern Scotland, noted for its ancient post office and traditional knitting patterns.
  • B. Forsinard
    Forsinard is a small village and railway station in the Scottish Highlands, known as a gateway to the surrounding Flow Country peatland wilderness.
  • C. Tippermuir
    Tippermuir is a locality in Scotland best known as the site of the 1644 Battle of Tippermuir during the Wars of the Three Kingdoms.
  • D. Ratho
    Ratho is a village in Edinburgh, Scotland, known for its historic canal-side setting and proximity to the Edinburgh International Climbing Arena.
  • E. Craignelder
    Craignelder is a notable summit in the Dungeon Hills range of Scotland’s Southern Uplands, known for its rugged upland terrain and hillwalking opportunities.
  • 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_69e0b518b8948190ad69cf9a8784d397 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e75dcb45f08190a9bcaa366964a2cb completed April 21, 2026, 11:21 a.m.
Created at: April 16, 2026, 4:25 p.m.