Triple

T2279871
Position Surface form Disambiguated ID Type / Status
Subject Leinster E51255 entity
Predicate containsRiver P165 FINISHED
Object River Boyne E79557 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 Boyne | Statement: [Leinster, containsRiver, River Boyne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Boyne
Context triple: [Leinster, containsRiver, River Boyne]
  • A. River Boyne chosen
    The River Boyne is a historically significant river in eastern Ireland, famed for the Battle of the Boyne and its rich archaeological and mythological heritage.
  • B. River Bain
    River Bain is a river in Lincolnshire, England, known for flowing through the town of Horncastle before joining the River Witham.
  • C. River Brosna
    River Brosna is a river in Ireland that flows through counties such as Westmeath and Offaly before joining the River Shannon.
  • D. Đáy River
    Đáy River is a significant river in northern Vietnam that flows through several provinces and districts, serving as an important waterway and agricultural resource.
  • E. River Loud
    River Loud is a small river in Lancashire, England, that flows through rural countryside before joining the River Ribble.
  • 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_69a88b08e4308190bdac9aebcca1c91a completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abc2194150819083156e4dcd45a423 completed March 7, 2026, 6:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1f76bb60819084cac16bce2ce55d completed March 9, 2026, 7:28 p.m.
Created at: March 4, 2026, 7:48 p.m.