Triple

T6490530
Position Surface form Disambiguated ID Type / Status
Subject River Lyon E148023 entity
Predicate flowsNear P350 FINISHED
Object Innerwick E515645 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: Innerwick | Statement: [River Lyon, flowsNear, Innerwick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Innerwick
Context triple: [River Lyon, flowsNear, Innerwick]
  • A. Innerwick chosen
    Innerwick is a small village in East Lothian, Scotland, known for its rural setting and historic parish church.
  • B. Addiewell
    Addiewell is a small village in West Lothian, Scotland, historically associated with shale oil mining and now also known for its modern prison facility.
  • C. Castlerock
    Castlerock is a small seaside village and popular holiday resort on the north coast of Northern Ireland.
  • D. Hillington
    Hillington is a small village and civil parish in Norfolk, England, known for its rural setting and historic country estate, Hillington Hall.
  • E. Wormhill
    Wormhill is a small rural village in Derbyshire, England, situated within the scenic Peak District National Park.
  • 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_69c009088f3081909cd467b05919de30 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c06a9a8d8481908d88e5c9f0c773f7 completed March 22, 2026, 10:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c65fdc835081909772f3a3aaee538f completed March 27, 2026, 10:45 a.m.
Created at: March 22, 2026, 4:53 p.m.