Triple

T17101633
Position Surface form Disambiguated ID Type / Status
Subject Keith E414992 entity
Predicate nearbyTown P3883 FINISHED
Object Fochabers E689774 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: Fochabers | Statement: [Keith, nearbyTown, Fochabers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fochabers
Context triple: [Keith, nearbyTown, Fochabers]
  • A. Fochabers chosen
    Fochabers is a historic village in Moray, northeastern Scotland, known for its traditional architecture and proximity to the River Spey.
  • B. Auchenblae
    Auchenblae is a small rural village in Aberdeenshire, Scotland, historically associated with agriculture and the surrounding Mearns countryside.
  • C. Kiltartan
    Kiltartan is a rural district in County Galway, Ireland, known for its rich Irish folklore and cultural heritage.
  • D. Kinglassie
    Kinglassie is a small village in Fife, Scotland, known historically for its coal mining heritage and rural character.
  • E. Fettercairn
    Fettercairn is a historic village in Aberdeenshire, Scotland, known for its picturesque setting, whisky distillery, and distinctive royal arch.
  • 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_69d886cfc8e88190b05ba466edd35591 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dc239a088190a776fe0f4361ffc7 completed April 18, 2026, 7:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a015fbe1d4c81909ce7e4626516b51d completed May 11, 2026, 4:49 a.m.
Created at: April 10, 2026, 5:35 a.m.