Triple

T22640969
Position Surface form Disambiguated ID Type / Status
Subject Duke of Gordon E558822 entity
Predicate associatedWith P37 FINISHED
Object Huntly 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: Huntly | Statement: [Duke of Gordon, associatedWith, Huntly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Huntly
Context triple: [Duke of Gordon, associatedWith, Huntly]
  • A. Huntly chosen
    Huntly is a historic town in Aberdeenshire, Scotland, long associated with the Gordon family and the Marquess of Huntly.
  • B. Huntly
    Huntly is a small town in New Zealand known for its coal mining history and location on the Waikato River between Hamilton and Auckland.
  • C. Huntly
    Huntly is a small town in Victoria, Australia, situated near Bendigo in the state's central region.
  • D. Queensburgh
    Queensburgh is a residential suburb and former borough situated inland to the west of central Durban in South Africa’s KwaZulu-Natal province.
  • E. Banchory
    Banchory is a small town in northeast Scotland situated on the River Dee, known for its scenic surroundings and role as a gateway to Royal Deeside.
  • 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_69e24547f7fc819086e2c4ba3b979657 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f170116fe881908178cffef26e3ae7 completed April 29, 2026, 2:42 a.m.
Created at: April 17, 2026, 3:04 p.m.