Triple
T54390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SEPTA Market–Frankford Line |
E1071
|
entity |
| Predicate | hasRollingStockType |
P1305
|
FINISHED |
| Object | electric multiple units |
—
|
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: electric multiple units | Statement: [SEPTA Market–Frankford Line, hasRollingStockType, electric multiple units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRollingStockType Context triple: [SEPTA Market–Frankford Line, hasRollingStockType, electric multiple units]
-
A.
rollingStockType
chosen
Indicates the specific category or type of railway rolling stock associated with an entity (e.g., locomotive, passenger car, freight wagon).
-
B.
hasLiftType
Indicates the specific type or category of lift associated with an entity.
-
C.
vehicleType
Indicates the specific kind or category of vehicle associated with an entity (e.g., car, bus, bicycle).
-
D.
hasRailSystem
Indicates that an entity possesses or is served by a rail-based transportation system.
-
E.
hasTrailType
Indicates that an entity (such as a trail or route) is associated with a specific type or category of trail.
- 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_69a248adc5b48190aa8db9fb092fb28a |
completed | Feb. 28, 2026, 1:45 a.m. |
| NER | Named-entity recognition | batch_69a24b3a9e848190b80de3c858678b3a |
completed | Feb. 28, 2026, 1:56 a.m. |
| PD | Predicate disambiguation | batch_69a24ac52fb08190aa7c38f83434f795 |
completed | Feb. 28, 2026, 1:54 a.m. |
Created at: Feb. 28, 2026, 1:50 a.m.