Triple

T17101600
Position Surface form Disambiguated ID Type / Status
Subject Keith E414992 entity
Predicate historicCounty P1069 FINISHED
Object Banffshire 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: Banffshire | Statement: [Keith, historicCounty, Banffshire]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Banffshire
Context triple: [Keith, historicCounty, Banffshire]
  • A. Banffshire chosen
    Banffshire is a historic county in northeast Scotland, known for its rugged coastline along the Moray Firth and its traditional fishing and agricultural communities.
  • B. Selkirkshire
    Selkirkshire is a historic county in the Scottish Borders, known for its rural landscapes and literary associations, particularly with Sir Walter Scott.
  • C. Perthshire
    Perthshire is a historic county in central Scotland known for its scenic Highlands landscapes, lochs, and rich cultural heritage.
  • D. Perthshire
    Perthshire is a historic county in central Scotland known for its scenic Highlands landscapes, lochs, and glens.
  • E. Perthshire
    Perthshire is a historic county in central Scotland known for its scenic lochs, mountains, and forests, often referred to as “Big Tree Country.”
  • 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_69d886cfc8e88190b05ba466edd35591 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dc239a088190a776fe0f4361ffc7 completed April 18, 2026, 7:31 p.m.
Created at: April 10, 2026, 5:35 a.m.