Triple

T17985532
Position Surface form Disambiguated ID Type / Status
Subject William fitzOsbern E430220 entity
Predicate built P1028 FINISHED
Object Monmouth 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: Monmouth Castle | Statement: [William fitzOsbern, built, Monmouth Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Monmouth Castle
Context triple: [William fitzOsbern, built, Monmouth Castle]
  • A. Monmouth Castle chosen
    Monmouth Castle is a historic medieval fortress in Monmouth, Wales, best known as the birthplace of King Henry V of England.
  • B. Oystermouth Castle
    Oystermouth Castle is a medieval stone fortress overlooking Swansea Bay in Wales, known for its Norman origins and well-preserved historic ruins.
  • C. Montgomery Castle
    Montgomery Castle is a historic medieval fortress located in the town of Montgomery in Powys, Wales.
  • D. Launceston Castle
    Launceston Castle is a medieval Norman fortress in Launceston, Cornwall, notable for its prominent motte-and-bailey design and historical role as an administrative center for the region.
  • E. Richmond Castle
    Richmond Castle is a well-preserved Norman fortress overlooking the River Swale in the market town of Richmond, England, known for its imposing keep and historic role in medieval border defense.
  • 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_69d8b90364248190a37381adea932f42 completed April 10, 2026, 8:46 a.m.
NER Named-entity recognition batch_69e4b29b4e808190af06074168169035 completed April 19, 2026, 10:46 a.m.
Created at: April 10, 2026, 10:23 a.m.