Triple
T22012034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Breda A650 |
E543599
|
entity |
| Predicate | hasPassengerAccessLevel |
P32331
|
FINISHED |
| Object | high-floor |
—
|
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: high-floor | Statement: [Breda A650, hasPassengerAccessLevel, high-floor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPassengerAccessLevel Context triple: [Breda A650, hasPassengerAccessLevel, high-floor]
-
A.
hasPassengerCheckInAccess
Indicates that an entity is permitted to perform or access passenger check-in functions for a given transport service or location.
-
B.
passengerAccess
chosen
Indicates that a passenger is allowed to enter, use, or move through a particular vehicle, area, or transportation-related facility.
-
C.
hasPassengerRole
Indicates that an entity participates in a context or event specifically in the capacity or role of a passenger.
-
D.
hasHumanAccess
Indicates that a human is able to access, use, or interact with the referenced entity or resource.
-
E.
hasTicketAccess
Indicates that an entity is permitted to view, use, or manage a particular ticket or set of tickets.
- 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_69e11e2db934819095556760c7d85e4d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127a520bc8190865f525a87255fb2 |
completed | April 28, 2026, 9:33 p.m. |
| PD | Predicate disambiguation | batch_69e6f62dc9d88190ae387f145f9528de |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:22 p.m.