Triple

T20858401
Position Surface form Disambiguated ID Type / Status
Subject Monument Street E513544 entity
Predicate runsNear P350 FINISHED
Object River Thames NE NERFINISHED

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 Thames | Statement: [Monument Street, runsNear, River Thames]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Thames
Context triple: [Monument Street, runsNear, 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. Thames
    Thames is a historic town on New Zealand’s North Island, known for its gold-mining heritage and position at the base of the Coromandel Peninsula.
  • C. Thames River
    The Thames River in Connecticut is a short tidal estuary in the southeastern part of the state that flows past cities like New London into Long Island Sound.
  • D. Thames River
    The Thames River is a Canadian river in southwestern Ontario that flows through communities such as Woodstock before emptying into Lake St. Clair.
  • E. Severn
    The Severn is the longest river in Great Britain, flowing through Wales and England before emptying into the Bristol Channel.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3a9fd7881908ae4c5c63f64efc0 completed April 21, 2026, 12:24 a.m.
Created at: April 16, 2026, 12:44 p.m.