Triple

T21255712
Position Surface form Disambiguated ID Type / Status
Subject Rougemont Castle E523861 entity
Predicate near P350 FINISHED
Object Exeter city walls 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: Exeter city walls | Statement: [Rougemont Castle, near, Exeter city walls]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Exeter city walls
Context triple: [Rougemont Castle, near, Exeter city walls]
  • A. Exeter City Walls chosen
    Exeter City Walls are a series of historic defensive fortifications encircling the city of Exeter, with origins dating back to the Roman period and later medieval expansions.
  • B. Exeter Castle
    Exeter Castle is a historic fortified complex in Exeter, England, long used as the city's principal stronghold and judicial center.
  • C. Bristol city wall
    The Bristol city wall was a medieval defensive fortification that once enclosed and protected the historic center of Bristol, England.
  • D. Oxford city walls
    The Oxford city walls are the medieval defensive fortifications that once enclosed and protected the historic center of Oxford, England.
  • E. Canterbury city walls
    The Canterbury city walls are a series of medieval defensive fortifications encircling the historic city of Canterbury in Kent, England.
  • 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_69e0b5146c108190adc9adb73e90abff completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e735a1f9e08190b494f582bcae5c35 completed April 21, 2026, 8:30 a.m.
Created at: April 16, 2026, 3:58 p.m.