Triple

T1579234
Position Surface form Disambiguated ID Type / Status
Subject The Boat Race E33722 entity
Predicate river P165 FINISHED
Object Thames E5226 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: Thames | Statement: [The Boat Race, river, Thames]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thames
Context triple: [The Boat Race, river, Thames]
  • A. Thames chosen
    The Thames is a major river in southern England that flows through London and has long been central to the country’s history, commerce, and culture.
  • B. Severn
    The Severn is the longest river in Great Britain, flowing through Wales and England before emptying into the Bristol Channel.
  • C. River Trent
    The River Trent is one of the principal rivers in the Midlands of England, flowing through cities such as Stoke-on-Trent and Nottingham before joining the Humber Estuary.
  • D. River Ouse
    The River Ouse is a major river in North Yorkshire, England, flowing through the historic city of York and forming part of the Humber river system before reaching the North Sea.
  • E. Werse
    The Werse is a river in North Rhine-Westphalia, Germany, known for flowing through the Münster region before joining the Ems.
  • 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_69a885f27a4c8190a4622252cdf54c00 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908d67bd08190afa8c504ed5273ee completed March 5, 2026, 4:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69aeb3a390bc8190891ebd5d8a48d818 completed March 9, 2026, 11:48 a.m.
Created at: March 4, 2026, 7:27 p.m.