Triple

T20004956
Position Surface form Disambiguated ID Type / Status
Subject Phil Dunster E494429 entity
Predicate familyName P18 FINISHED
Object Dunster 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: Dunster | Statement: [Phil Dunster, familyName, Dunster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dunster
Context triple: [Phil Dunster, familyName, Dunster]
  • A. Dunster chosen
    Dunster is a historic village in Somerset, England, renowned for its medieval castle, preserved architecture, and picturesque setting within Exmoor National Park.
  • B. Wherstead
    Wherstead is a small rural village and civil parish located just south of Ipswich in Suffolk, England, known for its agricultural landscape and proximity to the River Orwell.
  • C. Drewsteignton
    Drewsteignton is a rural village and civil parish on the edge of Dartmoor in Devon, England, known for its scenic countryside and historic landmarks.
  • D. Warminster
    Warminster is a suburban township in Bucks County, Pennsylvania, known for its residential communities, local commerce, and small general-aviation airport.
  • E. Warminster
    Warminster is a market town in Wiltshire, England, known for its historic architecture, surrounding countryside, and role as a local transport and service hub.
  • 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e661a46c748190a141ab5aac6ea250 completed April 20, 2026, 5:25 p.m.
Created at: April 11, 2026, 3:33 p.m.