Triple
T14169485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mamaroneck station |
E351167
|
entity |
| Predicate | railDirection |
P24810
|
FINISHED |
| Object | eastbound toward Stamford and New Haven |
—
|
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: eastbound toward Stamford and New Haven | Statement: [Mamaroneck station, railDirection, eastbound toward Stamford and New Haven]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railDirection Context triple: [Mamaroneck station, railDirection, eastbound toward Stamford and New Haven]
-
A.
transportDirection
chosen
Indicates the directional flow or route along which something is transported from an origin toward a destination.
-
B.
terminusDirection
Indicates the directional orientation or endpoint direction associated with a route, path, or line.
-
C.
railwayTrafficDirection
Indicates the customary side of the track on which trains are operated or expected to run within a given railway system or segment.
-
D.
trainNumberDirection
Indicates the specific direction in which a train, identified by its train number, is traveling or scheduled to travel.
-
E.
raceDirection
Indicates the directional orientation or path along which a race or racing event proceeds.
- 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_69d8278834a08190b0f1784e58d7b99c |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61b472288190b4a271daa54aa6cd |
completed | April 14, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69de05b8434c81908c33b1b513463b12 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 10, 2026, 1:01 a.m.