Triple

T10615035
Position Surface form Disambiguated ID Type / Status
Subject Kingsbridge Heights E276095 entity
Predicate near P350 FINISHED
Object Van Cortlandt Park E45596 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: Van Cortlandt Park | Statement: [Kingsbridge Heights, near, Van Cortlandt Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Van Cortlandt Park
Context triple: [Kingsbridge Heights, near, Van Cortlandt Park]
  • A. Van Cortlandt Park, Bronx chosen
    Van Cortlandt Park in the Bronx is one of New York City's largest public parks, known for its extensive woodlands, recreational facilities, and historic landscapes.
  • B. Bronx Park
    Bronx Park is a large urban park in New York City’s Bronx borough, best known as the home of the Bronx Zoo and the New York Botanical Garden.
  • C. Flushing County Park
    Flushing County Park is a public recreational area in Flushing, Michigan, offering outdoor amenities such as trails, picnic spaces, and natural scenery for community use.
  • D. Prospect Park
    Prospect Park is a public recreational park located in Wheat Ridge, Colorado, offering outdoor spaces and amenities for community use.
  • E. Prospect Park
    Prospect Park is a historic citrus grove and scenic public park in Redlands, California, known for its walking trails, orange trees, and cultural events.
  • 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_69d6aaf948d88190806cc3a8c47a3fb2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d6df5da6808190bd4cb486431dc42c completed April 8, 2026, 11:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e42d448fac81909137b0a0ed9b976e completed April 19, 2026, 1:17 a.m.
Created at: April 8, 2026, 7:33 p.m.