Triple

T19150025
Position Surface form Disambiguated ID Type / Status
Subject Robert, Count of Mortain E468779 entity
Predicate landholdingsRegion P10159 FINISHED
Object Cornwall E112827 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: Cornwall | Statement: [Robert, Count of Mortain, landholdingsRegion, Cornwall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cornwall
Context triple: [Robert, Count of Mortain, landholdingsRegion, Cornwall]
  • A. Cornwall chosen
    Cornwall is a county in the far southwest of England, known for its rugged coastline, Celtic heritage, and popular seaside tourism.
  • B. Cornwall
    Cornwall is a small town in central Prince Edward Island, Canada, located just west of the provincial capital, Charlottetown.
  • C. Cornwall
    Cornwall is a small borough in Lebanon County, Pennsylvania, historically known for its extensive iron ore deposits and the Cornwall Iron Furnace.
  • D. Devon
    Devon is a suburban community on the Philadelphia Main Line in Pennsylvania, best known for hosting the historic Devon Horse Show and Country Fair.
  • E. Devon
    Devon is a residential neighbourhood located within the city of Fredericton in New Brunswick, Canada.
  • 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e97c42348190875a2f5b5bc0b99e completed April 20, 2026, 8:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a06f25291f08190a7a337d0a51f380c completed May 15, 2026, 10:15 a.m.
Created at: April 10, 2026, 12:06 p.m.