Triple

T3077595
Position Surface form Disambiguated ID Type / Status
Subject A85 road E64173 entity
Predicate crosses P416 FINISHED
Object River Earn E140987 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 Earn | Statement: [A85 road, crosses, River Earn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Earn
Context triple: [A85 road, crosses, River Earn]
  • A. River Earn chosen
    River Earn is a river in central Scotland that flows from Loch Earn through Strathearn before joining the River Tay.
  • B. River Derwent
    The River Derwent is a major estuarine river in southeastern Tasmania, Australia, known for its scenic waterfront and as the waterway alongside the city of Hobart.
  • C. River Derwent
    The River Derwent is a river in North Yorkshire, England, that flows through the North York Moors and eventually joins the River Ouse, playing an important role in the region’s landscape and ecology.
  • D. River Derwent
    The River Derwent is a major river in Derbyshire, England, that flows through the Peak District and the city of Derby before joining the River Trent.
  • E. River Derwent
    The River Derwent is a major river in Cumbria, England, flowing through the Lake District and the town of Cockermouth before reaching the Irish Sea.
  • 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_69ad857a8aec8190bfdfd9c14554ac5a completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada1a6f6148190ae5cd6e45eda9006 completed March 8, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2035c404881908635c8514c8c1399 completed March 12, 2026, 12:05 a.m.
Created at: March 8, 2026, 3:02 p.m.