Triple

T8945328
Position Surface form Disambiguated ID Type / Status
Subject Turriff E213206 entity
Predicate hasNearbySettlement P4647 FINISHED
Object Banff E125100 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: Banff | Statement: [Turriff, hasNearbySettlement, Banff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Banff
Context triple: [Turriff, hasNearbySettlement, Banff]
  • A. Banff
    Banff is a resort town in the Canadian Rockies of Alberta, known for its stunning mountain scenery, hot springs, and role as a gateway to outdoor recreation in Banff National Park.
  • B. Banff chosen
    Banff is a historic town in Aberdeenshire, Scotland, known for its coastal setting on the Moray Firth and its well-preserved Georgian architecture.
  • C. Canmore
    Canmore is the online database of Scotland’s national record of the historic environment, documenting archaeological sites, buildings, and maritime heritage.
  • D. Canmore
    Canmore is a mountain town in Alberta, Canada, known for its scenic location in the Canadian Rockies near Banff National Park and its popularity for outdoor recreation.
  • E. Anmore
    Anmore is a small semi-rural village in Metro Vancouver, British Columbia, known for its forested setting and proximity to outdoor recreation areas.
  • 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_69ca839843408190a39069a029a89f15 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc66db998c8190999a7a686bbdda1f completed April 1, 2026, 12:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc1fcb44481908324220aeba1f4e2 completed April 3, 2026, 1:34 p.m.
Created at: March 30, 2026, 6:59 p.m.