Triple
T21670197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MARC fare system |
E534823
|
entity |
| Predicate | supportsPassengerType |
P138413
|
FINISHED |
| Object | adult passenger |
—
|
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: adult passenger | Statement: [MARC fare system, supportsPassengerType, adult passenger]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsPassengerType Context triple: [MARC fare system, supportsPassengerType, adult passenger]
-
A.
appliesToPassengerType
chosen
Indicates that a rule, condition, or attribute is relevant or restricted to a specific type or category of passenger.
-
B.
isPassengerOnly
Indicates that the subject entity is restricted to passenger use only and does not accommodate cargo, freight, or mixed-use purposes.
-
C.
hasPassengerArea
Indicates that an object or vehicle includes a designated area intended for carrying passengers.
-
D.
passengerCapacityCategory
Indicates the classification of an entity based on the number of passengers it is designed or allowed to carry.
-
E.
hasPassengerOnlyService
Indicates that the service provided involves only the transportation of passengers, with no freight or cargo component.
- 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_69e0c46898008190aa618a4af55bd1ee |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef8a0a9b4481909477245d53f99cb0 |
completed | April 27, 2026, 4:08 p.m. |
| PD | Predicate disambiguation | batch_69e6968abfdc81909cf9e0bd72db9eca |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:37 p.m.