Triple

T799557
Position Surface form Disambiguated ID Type / Status
Subject Port Jersey Marine Terminal E17098 entity
Predicate waterbody P1489 FINISHED
Object Upper New York Bay E1835 NE FINISHED

How this triple was built (3 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: Upper New York Bay | Statement: [Port Jersey Marine Terminal, waterbody, Upper New York Bay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Upper New York Bay
Context triple: [Port Jersey Marine Terminal, waterbody, Upper New York Bay]
  • A. Upper New York Bay chosen
    Upper New York Bay is a tidal estuary in New York Harbor, bordered by Manhattan, Brooklyn, Staten Island, and New Jersey, that serves as a major shipping channel and gateway between the Atlantic Ocean and the inland waterways of the northeastern United States.
  • B. Lower New York Bay
    Lower New York Bay is a tidal estuary at the mouth of the Hudson River that forms part of New York Harbor and serves as a major gateway for maritime traffic between the Atlantic Ocean and the New York metropolitan area.
  • C. Flushing Bay
    Flushing Bay is a tidal embayment in northern Queens, New York City, forming part of the East River and lying adjacent to major landmarks such as LaGuardia Airport and Citi Field.
  • D. New York Bight
    New York Bight is a broad, shallow indentation of the Atlantic coastline off New York and New Jersey, known for its busy shipping lanes, rich marine ecosystems, and proximity to the New York metropolitan area.
  • E. Jamaica Bay
    Jamaica Bay is a large, wildlife-rich estuary on the southern shore of Long Island in New York City, known for its marshes, bird habitats, and inclusion within the Gateway National Recreation Area.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: waterbody
Context triple: [Port Jersey Marine Terminal, waterbody, Upper New York Bay]
  • A. bodyOfWater
    Indicates that one entity is a body of water that is geographically or physically associated with another entity.
  • B. waterbodyType
    Indicates the classification of a water body according to its type (e.g., river, lake, ocean, etc.).
  • C. locatedOnWaterbody chosen
    Indicates that an entity is situated on or directly adjacent to a specified body of water.
  • D. hasWaterBodyOnWest
    Indicates that a specified entity has a water body located to its west.
  • E. mouthOfWatercourse
    Indicates the location where a watercourse ends and flows into a larger body of water or another watercourse.
  • F. None of above.

Provenance (4 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_69a49378b9c48190adbf5f62e5b7aca1 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a7cb26dc8190bdd3a278b8695873 completed March 1, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac99669a1481909fa42162ffee2d7b completed March 7, 2026, 9:32 p.m.
PD Predicate disambiguation batch_69a4a5122a008190b0c621b7bc588d41 completed March 1, 2026, 8:44 p.m.
Created at: March 1, 2026, 7:38 p.m.