Triple

T18175841
Position Surface form Disambiguated ID Type / Status
Subject Sidlaws E435154 entity
Predicate region P40 FINISHED
Object Tayside 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: Tayside | Statement: [Sidlaws, region, Tayside]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tayside
Context triple: [Sidlaws, region, Tayside]
  • A. Tayside chosen
    Tayside is a former administrative region in eastern Scotland that included areas such as Angus, Dundee, and Perth and Kinross.
  • B. Ayrshire
    Ayrshire is a historic county and coastal region in southwest Scotland known for its agriculture, seaside towns, and associations with poet Robert Burns.
  • C. West Scotland
    West Scotland is a coastal region of western Scotland known for its rugged landscapes, islands, and maritime communities.
  • D. Grampian
    Grampian was a former local government region in northeast Scotland, centered on the city of Aberdeen and known for its North Sea oil industry and agricultural hinterland.
  • E. Lothian and Fife
    Lothian and Fife are historic regions of eastern Scotland situated on opposite shores of the Firth of Forth, encompassing major urban centers such as Edinburgh and Dunfermline.
  • 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_69d8b90c7ec081909b4694ccecb449c6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4df59bf3881909adc28cacbe9cb39 completed April 19, 2026, 1:57 p.m.
Created at: April 10, 2026, 10:30 a.m.