Triple

T15946971
Position Surface form Disambiguated ID Type / Status
Subject Banchory E386709 entity
Predicate locatedOnRiver P165 FINISHED
Object River Dee E78595 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: River Dee | Statement: [Banchory, locatedOnRiver, River Dee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Dee
Context triple: [Banchory, locatedOnRiver, River Dee]
  • A. River Dee
    River Dee is a river in northeastern Ireland that flows through County Louth and neighboring counties before emptying into the Irish Sea.
  • B. River Dee chosen
    River Dee is a major river in northeastern Scotland that flows through the Cairngorms and Royal Deeside, renowned for its scenic beauty and association with the British royal family.
  • C. River Dee
    The River Dee is a historically significant river in the United Kingdom that flows through Wales and England, notably passing through the city of Chester before reaching the Irish Sea.
  • D. River Dee (Galloway)
    River Dee (Galloway) is a river in southwest Scotland that flows through the Galloway region from the Southern Uplands to the Solway Firth.
  • E. Chocolate River
    Chocolate River is the fantastical flowing river of liquid chocolate inside Willy Wonka’s magical candy factory in Roald Dahl’s story.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156d1a4c08190afc325491ba38870 completed April 16, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5a5b0dc81909606d667c3bc0edf completed May 9, 2026, 10:31 p.m.
Created at: April 10, 2026, 4:53 a.m.