Triple

T12346727
Position Surface form Disambiguated ID Type / Status
Subject Lossiemouth E294374 entity
Predicate hasRiver P165 FINISHED
Object River Lossie E414993 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 Lossie | Statement: [Lossiemouth, hasRiver, River Lossie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Lossie
Context triple: [Lossiemouth, hasRiver, River Lossie]
  • A. River Lossie chosen
    The River Lossie is a river in northeast Scotland that flows through the town of Elgin before emptying into the Moray Firth.
  • B. River Roden
    River Roden is a small river in Shropshire, England, that flows through rural countryside before joining the River Tern.
  • C. River Colligan
    River Colligan is a river in County Waterford, Ireland, known for flowing through the town of Dungarvan before entering Dungarvan Bay.
  • D. River Jones Johnson
    River Jones Johnson is the son of American model and media personality Paulina Gretzky and professional golfer Dustin Johnson.
  • E. River Cardinham
    River Cardinham is a small river in Cornwall, England, that flows through Cardinham parish before joining the River Fowey.
  • 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_69d6ab6ccbec8190b09e2d357aa80064 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f7a4a448190aa70d66dc2f406c1 completed April 10, 2026, 6:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f62aae8d7c8190a722c28a5a153d1d completed May 2, 2026, 4:47 p.m.
Created at: April 8, 2026, 9:53 p.m.