Triple

T17337773
Position Surface form Disambiguated ID Type / Status
Subject Buchan E420985 entity
Predicate hasBorderWith P224 FINISHED
Object Formartine E629560 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: Formartine | Statement: [Buchan, hasBorderWith, Formartine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Formartine
Context triple: [Buchan, hasBorderWith, Formartine]
  • A. Formartine chosen
    Formartine is a committee area and historic district in Aberdeenshire, Scotland, encompassing a mix of rural communities, coastal towns, and agricultural land.
  • B. Foulis
    Foulis is the traditional Highland estate and seat associated with Clan Munro in Scotland.
  • C. Cunninghame
    Cunninghame is a historic district in southwestern Scotland, traditionally forming part of Ayrshire.
  • D. Faifley
    Faifley is a residential area and housing estate on the outskirts of Clydebank in West Dunbartonshire, Scotland.
  • E. Cromvoirt
    Cromvoirt is a small village in the Dutch province of North Brabant, known for its rural character and proximity to the city of ’s-Hertogenbosch.
  • 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_69d889d3adc881909319f1edb8d2a956 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a12e1288190a81c30d6e1e9652f completed April 19, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a018c56c8148190ab6e3e2eff09725e completed May 11, 2026, 7:59 a.m.
Created at: April 10, 2026, 5:43 a.m.