Triple

T18012588
Position Surface form Disambiguated ID Type / Status
Subject Central Business District of Perth E430918 entity
Predicate hasLandmark P105 FINISHED
Object Langley 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: Langley Park | Statement: [Central Business District of Perth, hasLandmark, Langley Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Langley Park
Context triple: [Central Business District of Perth, hasLandmark, Langley Park]
  • A. Langley Park chosen
    Langley Park is a large riverside public park in central Perth, Western Australia, known for its open lawns, events, and views over the Swan River.
  • B. Devonshire Park
    Devonshire Park is a cultural and sports complex in Eastbourne, England, known for its historic tennis courts and proximity to major arts and entertainment venues.
  • C. Devonshire Park
    Devonshire Park is a public green space and recreational park located in the town of Keighley in West Yorkshire, England.
  • D. Courtland Park
    Courtland Park is a public recreational park located in Reidsville, North Carolina.
  • E. Clarendon Park
    Clarendon Park is a public park and community recreation area located in Chicago’s Uptown neighborhood.
  • 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b520ea088190b74903f1e1ba49e2 completed April 19, 2026, 10:57 a.m.
Created at: April 10, 2026, 10:24 a.m.