Triple

T1599836
Position Surface form Disambiguated ID Type / Status
Subject Leyland E34365 entity
Predicate hasPark P105 FINISHED
Object Worden Park E226304 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: Worden Park | Statement: [Leyland, hasPark, Worden Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Worden Park
Context triple: [Leyland, hasPark, Worden Park]
  • A. Worden Park chosen
    Worden Park is a large historic public park in Leyland, Lancashire, known for its woodlands, formal gardens, and recreational facilities.
  • B. Browne Park
    Browne Park is a prominent rugby league stadium in Rockhampton, Queensland, known for hosting local and regional sporting events.
  • C. Pullen Park
    Pullen Park is a historic public park in Raleigh, North Carolina, known for its scenic grounds, carousel, and family-friendly recreational attractions.
  • D. Wilacre Park
    Wilacre Park is a popular urban park and hiking area in the Studio City neighborhood of Los Angeles, known for its scenic trails and views of the San Fernando Valley.
  • E. Glover Park
    Glover Park is a residential neighborhood in Washington, D.C. known for its tree-lined streets, row houses, and proximity to parks and embassies.
  • 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_69a885fdcb9c819081ce6f0b8cd477dd completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a9094a27908190bf0d9b5d43617192 completed March 5, 2026, 4:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae1fb8b14c8190abbcc24f17fa8243 completed March 9, 2026, 1:17 a.m.
Created at: March 4, 2026, 7:28 p.m.