Triple

T6449491
Position Surface form Disambiguated ID Type / Status
Subject Royal Canal E139826 entity
Predicate crosses P416 FINISHED
Object River Inny E263619 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 Inny | Statement: [Royal Canal, crosses, River Inny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Inny
Context triple: [Royal Canal, crosses, River Inny]
  • A. River Inny chosen
    The River Inny is a significant river in Ireland that flows through counties such as Longford and Westmeath before joining the River Shannon.
  • B. River Inny
    The River Inny is a river in Cornwall, England, known for flowing through rural landscapes before joining the River Tamar.
  • C. River Braid
    River Braid is a river in County Antrim, Northern Ireland, that flows through the town of Ballymena and is a tributary of the River Main.
  • D. River Scaur
    River Scaur is a Scottish river in Dumfries and Galloway that flows through rural valleys before joining the River Nith.
  • E. River Gowan
    River Gowan is a small river in Cumbria, England, that flows through the Lake District and joins the River Kent near Staveley.
  • 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_69c008b301948190a35854e5284dc822 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c069b2c7bc81908c683ec22cad9628 completed March 22, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cb02cb3c8190917842bb654326ee completed March 27, 2026, 6:22 p.m.
Created at: March 22, 2026, 4:47 p.m.