Triple

T21411643
Position Surface form Disambiguated ID Type / Status
Subject River Laver E528185 entity
Predicate flowsNear P350 FINISHED
Object Ripon 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: Ripon | Statement: [River Laver, flowsNear, Ripon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ripon
Context triple: [River Laver, flowsNear, Ripon]
  • A. Ripon
    Ripon is a small city in California’s Central Valley known for its agricultural roots and tight-knit community.
  • B. Ripon chosen
    Ripon is a historic cathedral city in North Yorkshire, England, known for Ripon Cathedral and its traditional hornblower ceremony.
  • C. City of York
    The City of York is a historic cathedral city in North Yorkshire, England, renowned for its medieval walls, Gothic York Minster, and well-preserved old town.
  • D. Chester
    Chester is a historic walled city in northwest England known for its Roman heritage, medieval architecture, and distinctive two-tiered shopping galleries called the Rows.
  • E. Chester
    Chester is a historic walled city in northwest England, renowned for its well-preserved Roman and medieval architecture.
  • 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_69e0c454c248819093425d1099101c09 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b1fe2cd08190bfaf28daae4f5233 completed April 22, 2026, 11:33 a.m.
Created at: April 16, 2026, 5:43 p.m.