Triple

T10351212
Position Surface form Disambiguated ID Type / Status
Subject One57 E243885 entity
Predicate overlooks P1323 FINISHED
Object Central Park E5448 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: Central Park | Statement: [One57, overlooks, Central Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Central Park
Context triple: [One57, overlooks, Central Park]
  • A. Central Park chosen
    Central Park is a large, iconic urban park in the heart of Manhattan, known for its landscaped grounds, recreational spaces, and cultural significance.
  • B. Central Park
    Central Park is a large circular public park at the heart of Connaught Place in New Delhi, known for its open green space, amphitheater, and role as a popular recreational and cultural hub.
  • C. Central Park
    Central Park is a football stadium in Cowdenbeath, Scotland, best known as the long-time home ground of Cowdenbeath F.C.
  • D. Central Park
    Central Park is an animated musical comedy television series that follows the quirky Tillerman family as they protect and manage New York City's iconic Central Park.
  • E. Central Park
    Central Park is a major public park in Grand Prairie, Texas, featuring recreational facilities, green spaces, and community amenities.
  • 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_69d381b22b8c8190aaed476be5f872a9 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9489f9481908fc1c818e81c1cc2 completed April 7, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69d75001586c8190a0d4af1ff5588f0e completed April 9, 2026, 7:06 a.m.
Created at: April 6, 2026, 11:57 a.m.