Triple

T17474185
Position Surface form Disambiguated ID Type / Status
Subject River Findhorn E425494 entity
Predicate flowsNear P350 FINISHED
Object Forres 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: Forres | Statement: [River Findhorn, flowsNear, Forres]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Forres
Context triple: [River Findhorn, flowsNear, Forres]
  • A. Forres chosen
    Forres is a historic town in northeastern Scotland known for its ancient monuments and links to Shakespeare’s Macbeth.
  • B. Arbirlot
    Arbirlot is a small rural village in the Angus council area of eastern Scotland, known for its historic parish church and scenic countryside setting near the North Sea coast.
  • C. Crieff
    Crieff is a historic market town in central Scotland known for its scenic setting on the edge of the Highlands and its role as a gateway to Perthshire.
  • D. Dufftown
    Dufftown is a small Scottish town in the Speyside region renowned for its concentration of whisky distilleries and central role in Scotch whisky production.
  • E. Maybole
    Maybole is a historic small town in South Ayrshire, Scotland, traditionally regarded as the capital of the Carrick district.
  • 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_69d889dbc2e88190b18ea6115e819258 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451baa7b0819092035fec42305397 completed April 19, 2026, 3:53 a.m.
Created at: April 10, 2026, 5:47 a.m.