Triple

T19833916
Position Surface form Disambiguated ID Type / Status
Subject Roker E476533 entity
Predicate hasFeature P182 FINISHED
Object Roker Park 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: Roker Park | Statement: [Roker, hasFeature, Roker Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roker Park
Context triple: [Roker, hasFeature, Roker Park]
  • A. Roker Park chosen
    Roker Park is a coastal public park in Sunderland, England, known for its landscaped gardens, recreational facilities, and proximity to Roker Beach.
  • B. Roker Park
    Roker Park was the historic football stadium in Sunderland, England, that served as the long-time home ground of Sunderland A.F.C. until its closure and demolition in the late 20th century.
  • C. Brandon Hill park
    Brandon Hill park is a historic public green space in Bristol, England, known for its panoramic city views, wooded paths, and the prominent Cabot Tower landmark.
  • D. Loftin Park
    Loftin Park is a local public park in the city of Bellaire, Texas, providing outdoor recreational space for residents and visitors.
  • E. Powerhouse Park
    Powerhouse Park is a popular oceanfront park in Del Mar, California, known for its grassy bluffs, beach access, and scenic coastal views.
  • 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_69d8e51c7c188190b926f3a2a7b5f881 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e656d0347c8190b586c7fe01b61e97 completed April 20, 2026, 4:39 p.m.
Created at: April 10, 2026, 1:50 p.m.