Triple

T16786563
Position Surface form Disambiguated ID Type / Status
Subject Horncastle E407994 entity
Predicate hasRiver P165 FINISHED
Object River Waring 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 Waring | Statement: [Horncastle, hasRiver, River Waring]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Waring
Context triple: [Horncastle, hasRiver, River Waring]
  • A. River Waring chosen
    The River Waring is a small river in Lincolnshire, England, that flows through the Lincolnshire Wolds before joining the River Bain.
  • B. Waters River
    Waters River is a small waterway in Massachusetts that flows through the town of Danvers.
  • C. Fales River
    Fales River is a smaller watercourse in Nova Scotia, Canada, that serves as a tributary feeding into the larger Annapolis River system.
  • D. Hayes River
    The Hayes River is a remote waterway in northern Manitoba, Canada, that flows into Hudson Bay and historically served as an important route for the fur trade.
  • E. Walkill River
    The Walkill River is a north-flowing river in New Jersey and New York that drains part of the Appalachian Valley before joining the Hudson River.
  • 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_69d8839270588190886720d9519bbf8f completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b21a52ac8190b4374aa0fc45683a completed April 18, 2026, 4:32 p.m.
Created at: April 10, 2026, 5:22 a.m.