Triple

T28602410
Position Surface form Disambiguated ID Type / Status
Subject Valhalla Metro-North station E723947 entity
Predicate adjacentStationOnHarlemLineNorthbound P90734 FINISHED
Object Mount Pleasant station
Mount Pleasant station is a small Metro-North Railroad stop on the Harlem Line in Westchester County, New York, primarily serving the Kensico Cemetery area.
E1826614 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: Mount Pleasant station | Statement: [Valhalla Metro-North station, adjacentStationOnHarlemLineNorthbound, Mount Pleasant station]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mount Pleasant station
Triple: [Valhalla Metro-North station, adjacentStationOnHarlemLineNorthbound, Mount Pleasant station]
Generated description
Mount Pleasant station is a small Metro-North Railroad stop on the Harlem Line in Westchester County, New York, primarily serving the Kensico Cemetery area.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: adjacentStationOnHarlemLineNorthbound
Context triple: [Valhalla Metro-North station, adjacentStationOnHarlemLineNorthbound, Mount Pleasant station]
  • A. adjacentStationOnHarlemLine chosen
    Indicates that one station is directly next to another station along the Harlem Line, with no other station in between.
  • B. adjacentStationOnBMTBroadwayLine
    Indicates that one station is directly next to another station along the BMT Broadway subway line, with no other stations in between.
  • C. adjacentStationTowardNYC
    Indicates that one station is directly next to another in the direction toward New York City.
  • D. adjacentStationOnFarRockawayBranch
    Indicates that one station is directly next to another station along the Far Rockaway branch of the rail network.
  • E. adjacentStationOnINDSixthAvenueLine
    Indicates that one station is directly next to another station along the IND Sixth Avenue subway line.
  • F. None of above.

Provenance (6 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_69f01d80b1908190980594837604b8c7 completed April 28, 2026, 2:37 a.m.
NER Named-entity recognition batch_69f6d0d46aec819091edf97324d793ac completed May 3, 2026, 4:36 a.m.
NED1 Entity disambiguation (via context triple) batch_6a1cb703bca48190b1ff54262fb7a12f completed May 31, 2026, 10:32 p.m.
NEDg Description generation batch_6a1cbaaa69348190a4e8de0490e66edf completed May 31, 2026, 10:48 p.m.
NED2 Entity disambiguation (via description) batch_6a1cbb5d90ec819093705eae50314f33 completed May 31, 2026, 10:51 p.m.
PD Predicate disambiguation batch_69f6cfe2183481908ae4e85a59c66f69 completed May 3, 2026, 4:32 a.m.
Created at: April 28, 2026, 4:25 a.m.