Triple

T17956642
Position Surface form Disambiguated ID Type / Status
Subject West Dorset E448966 entity
Predicate containsSettlement P847 FINISHED
Object Puddletown E1123929 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: Puddletown | Statement: [West Dorset, containsSettlement, Puddletown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Puddletown
Context triple: [West Dorset, containsSettlement, Puddletown]
  • A. Puddletown chosen
    Puddletown is a historic village in Dorset, England, known for its traditional architecture and rural setting in the Piddle Valley.
  • B. Dalmally
    Dalmally is a small village in Argyll and Bute, western Scotland, known for its scenic Highland setting and proximity to Loch Awe.
  • C. Sandwick
    Sandwick is a small settlement associated with the area of Martindale, likely a rural hamlet or village in the United Kingdom.
  • D. Sandwick
    Sandwick is a rural parish in Orkney, Scotland, known for its coastal landscapes and proximity to several important Neolithic archaeological sites.
  • E. Polperro
    Polperro is a picturesque historic fishing village and popular tourist destination on the south coast of Cornwall, England.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4afb0afe08190964e771ec632fa1e completed April 19, 2026, 10:34 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0329211004819095d9e16c82b6f338 completed May 12, 2026, 1:20 p.m.
Created at: April 10, 2026, 10:21 a.m.