Triple

T21946066
Position Surface form Disambiguated ID Type / Status
Subject William Poole E541936 entity
Predicate familyName P18 FINISHED
Object Poole 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: Poole | Statement: [William Poole, familyName, Poole]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Poole
Context triple: [William Poole, familyName, Poole]
  • A. Poole chosen
    Poole is a coastal town and seaport in Dorset, England, known for its large natural harbour and maritime activities.
  • B. Bournemouth
    Bournemouth is a large coastal resort town on England’s south coast, known for its sandy beaches, tourism, and role as a regional commercial and transport hub.
  • C. Bridgwater
    Bridgwater is a historic market town in Somerset, England, known for its maritime heritage and role in regional trade and industry.
  • D. Yeovil
    Yeovil is a town in Somerset, England, known historically for its aircraft and defence industries and serving as a commercial and service hub for the surrounding rural area.
  • E. Bideford
    Bideford is a small rural settlement in the Carterton District of New Zealand’s Wairarapa region.
  • 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_69e0c47ef0e48190a50e1bcc43f4b3fd completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f12427c2b48190949c41bd3be2d9f3 completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:57 p.m.