Triple

T17011272
Position Surface form Disambiguated ID Type / Status
Subject Etu-Töölö E412704 entity
Predicate hasLandmark P105 FINISHED
Object Hesperia 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: Hesperia Park | Statement: [Etu-Töölö, hasLandmark, Hesperia Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hesperia Park
Context triple: [Etu-Töölö, hasLandmark, Hesperia Park]
  • A. Hesperia Park chosen
    Hesperia Park is a public green space located in the Töölö district of Helsinki, Finland.
  • B. Almansor Park
    Almansor Park is a public recreational park in Alhambra, California, featuring sports facilities, open green spaces, and community amenities.
  • C. Ramona Park
    Ramona Park is a public recreational park in Portage, Michigan, known for its lakeside setting and outdoor amenities.
  • D. Occidental Park
    Occidental Park is a public urban park and gathering space in Seattle’s historic Pioneer Square neighborhood, known for its art installations, events, and proximity to downtown attractions.
  • E. Hesperia Lake Park
    Hesperia Lake Park is a public recreational area in Hesperia, California, known for its fishing lake, camping facilities, and outdoor community events.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d47bcb508190a799f0bad6b70245 completed April 18, 2026, 6:59 p.m.
Created at: April 10, 2026, 5:33 a.m.