Triple

T23142016
Position Surface form Disambiguated ID Type / Status
Subject House of Devereux E577487 entity
Predicate region P40 FINISHED
Object Herefordshire 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: Herefordshire | Statement: [House of Devereux, region, Herefordshire]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Herefordshire
Context triple: [House of Devereux, region, Herefordshire]
  • A. Herefordshire chosen
    Herefordshire is a predominantly rural county in the West Midlands of England, known for its agriculture, rolling countryside, and the cathedral city of Hereford.
  • B. Wiltshire
    Wiltshire is a historic rural county in South West England known for landmarks such as Stonehenge, Salisbury Cathedral, and its longstanding military presence.
  • C. Shropshire
    Shropshire is a largely rural county in the West Midlands of England, known for its historic market towns, rolling countryside, and parts of the Shropshire Hills Area of Outstanding Natural Beauty.
  • D. Gloucestershire
    Gloucestershire is a historic county in South West England known for its rural Cotswolds landscapes, cathedral city of Gloucester, and rich medieval heritage.
  • E. Somerset
    Somerset is a historic county in South West England known for its rural landscapes, coastal areas, and cities such as Bath and Wells.
  • 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_69e245f8e6248190ba3d58e068b4dccb completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18eca8a9081908dcc39409f615b7c completed April 29, 2026, 4:53 a.m.
Created at: April 17, 2026, 4 p.m.