Triple

T20040889
Position Surface form Disambiguated ID Type / Status
Subject York Assize Courts E497410 entity
Predicate adjacentTo P224 FINISHED
Object York Castle 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: York Castle | Statement: [York Assize Courts, adjacentTo, York Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: York Castle
Context triple: [York Assize Courts, adjacentTo, York Castle]
  • A. York Castle chosen
    York Castle is a historic fortified complex in York, England, long used as a royal stronghold, administrative center, and prison.
  • B. Oxford Castle
    Oxford Castle is a historic Norman medieval castle and former prison in Oxford, England, now partly preserved as a tourist attraction and heritage site.
  • C. Bristol Castle
    Bristol Castle was a major medieval fortress in Bristol, England, that served as a strategic stronghold and royal prison during the Norman and later periods.
  • D. Canterbury Castle
    Canterbury Castle is a Norman-era stone fortress in Canterbury, Kent, now a historic ruin and one of England’s oldest surviving castles.
  • E. Winchester Castle
    Winchester Castle is a historic medieval royal fortress in Winchester, England, long associated with the English monarchy and government.
  • 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_69da627278c88190babe4297a9df1236 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e662eb9a6081909d06dc1d457b4d5a completed April 20, 2026, 5:31 p.m.
Created at: April 11, 2026, 3:36 p.m.