Triple

T1178133
Position Surface form Disambiguated ID Type / Status
Subject Mott Haven E25074 entity
Predicate hasLandmark P105 FINISHED
Object Madison Avenue Bridge E25073 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: Madison Avenue Bridge | Statement: [Mott Haven, hasLandmark, Madison Avenue Bridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madison Avenue Bridge
Context triple: [Mott Haven, hasLandmark, Madison Avenue Bridge]
  • A. Madison Avenue Bridge chosen
    The Madison Avenue Bridge is a historic swing bridge in New York City that carries Madison Avenue traffic between Manhattan and the Bronx.
  • B. Park Avenue Bridge
    The Park Avenue Bridge is a vertical-lift railroad bridge in New York City that carries Metro-North Railroad tracks between Manhattan and the Bronx.
  • C. 59th Street Bridge
    The 59th Street Bridge, officially known as the Queensboro Bridge, is a major cantilever bridge in New York City that spans the East River between Manhattan and Queens.
  • D. Third Avenue Bridge
    The Third Avenue Bridge is a major swing bridge in New York City that carries traffic between Manhattan and the Bronx.
  • E. Willis Avenue Bridge
    The Willis Avenue Bridge is a swing bridge in New York City that carries traffic between Manhattan and the Bronx.
  • 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_69a494267b4c819088c97a59182bf56a completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bd10ccc481908d5bcef648aab3c1 completed March 1, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69afbba1649081909703163de2d018cd completed March 10, 2026, 6:35 a.m.
Created at: March 1, 2026, 7:45 p.m.