Triple

T8120959
Position Surface form Disambiguated ID Type / Status
Subject Kimbolton Castle E189605 entity
Predicate near P350 FINISHED
Object River Kym E286480 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 Kym | Statement: [Kimbolton Castle, near, River Kym]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Kym
Context triple: [Kimbolton Castle, near, River Kym]
  • A. River Kym chosen
    River Kym is a small river in England that flows through Cambridgeshire and Bedfordshire before joining the River Great Ouse.
  • B. River Kello
    River Kello is a small river in Dumfries and Galloway, Scotland, known as one of the tributaries feeding into the River Nith within the region’s rural landscape.
  • C. Kyam River
    The Kyam River is a lesser-known river in central India that serves as a tributary within the Ken River basin.
  • D. River Tutt
    River Tutt is a small river in North Yorkshire, England, that flows through the Vale of Mowbray before joining the River Ure.
  • E. River Kale
    The River Kale is a small river in the Scottish Borders that rises in the Cheviot Hills and flows through rural Northumberland and Roxburghshire before joining the River Teviot.
  • 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_69ca82bb74848190afb1f18640632c10 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb435b72888190ad6330b375ed1eff completed March 31, 2026, 3:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc9454ccb48190b0f894bed5da8a01 completed April 1, 2026, 3:43 a.m.
Created at: March 30, 2026, 5:33 p.m.