Triple

T15946989
Position Surface form Disambiguated ID Type / Status
Subject Banchory E386709 entity
Predicate nearbySettlement P350 FINISHED
Object Aboyne E423117 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: Aboyne | Statement: [Banchory, nearbySettlement, Aboyne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aboyne
Context triple: [Banchory, nearbySettlement, Aboyne]
  • A. Aboyne chosen
    Aboyne is a village in Aberdeenshire, Scotland, known for its scenic Deeside location and annual Highland Games.
  • B. Hyndland
    Hyndland is an affluent residential district in Glasgow known for its historic tenement buildings, leafy streets, and vibrant local amenities.
  • C. Atholl
    Atholl is a historic region and former earldom in the Scottish Highlands, known for its rugged landscapes, clan heritage, and association with the Dukes of Atholl.
  • D. Atholl
    Atholl is an affluent residential suburb located within the city of Sandton in Johannesburg, South Africa.
  • E. Auchterderran
    Auchterderran is a small village and parish in Fife, Scotland, with historical ties to coal mining and close links to the nearby town of Cardenden.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156d1a4c08190afc325491ba38870 completed April 16, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69fff291a4308190bd5b45dfdb3a6b98 completed May 10, 2026, 2:50 a.m.
Created at: April 10, 2026, 4:53 a.m.