Triple
T3312645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metro-North Railroad Port Jervis Line |
E69607
|
entity |
| Predicate | connectsToService |
P845
|
FINISHED |
| Object | PATH trains at Hoboken |
—
|
LITERAL 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: PATH trains at Hoboken | Statement: [Metro-North Railroad Port Jervis Line, connectsToService, PATH trains at Hoboken]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsToService Context triple: [Metro-North Railroad Port Jervis Line, connectsToService, PATH trains at Hoboken]
-
A.
connectsTo
chosen
Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
-
B.
hasServiceTo
Indicates that one entity provides, offers, or operates a service for or directed toward another entity.
-
C.
connectsToSeries
Indicates that one entity is linked or associated with a particular series, establishing a connection or membership relationship between them.
-
D.
connectionTo
Indicates a relationship in which one entity is linked, associated, or otherwise related to another entity.
-
E.
operatesServiceTo
Indicates that one entity runs or provides a transportation or service route to another entity or location.
- F. None of above.
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_69ad85a0bb048190a5458d2738012d61 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0eddf488190b7f05b3903b96d4b |
completed | March 8, 2026, 5:25 p.m. |
| PD | Predicate disambiguation | batch_69ada4282730819092aa39c5f9269df0 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:11 p.m.