Triple

T16547717
Position Surface form Disambiguated ID Type / Status
Subject Sketty E401986 entity
Predicate near P350 FINISHED
Object Singleton Park E874764 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: Singleton Park | Statement: [Sketty, near, Singleton Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Singleton Park
Context triple: [Sketty, near, Singleton Park]
  • A. Singleton Park chosen
    Singleton Park is a large public park in Swansea, Wales, known for its botanical gardens, ornamental lakes, and as the scenic setting for part of Swansea University's campus.
  • B. Stone Park
    Stone Park is a local public park in Ashland, Massachusetts, used for community recreation and outdoor activities.
  • C. Monrepos Park
    Monrepos Park is a historic landscape park and former manor estate on an island in Vyborg, Russia, known for its romantic rocky scenery and picturesque views of the Gulf of Finland.
  • D. Topstone Park
    Topstone Park is a natural recreational area in Redding, Connecticut, known for its wooded trails, swimming pond, and outdoor activities.
  • E. Sand Hill Park
    Sand Hill Park is a public recreational park located in Essex, Vermont, offering outdoor space and amenities for community activities and leisure.
  • 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_69d88384bc30819084229e7dcdc39a41 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e34fbf79048190b761008441762374 completed April 18, 2026, 9:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a008a2590d48190b72b7d5be20c14c7 completed May 10, 2026, 1:37 p.m.
Created at: April 10, 2026, 5:15 a.m.