Triple
T19656826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hiroo Station |
E471968
|
entity |
| Predicate | ticketingMethods |
P115850
|
FINISHED |
| Object | IC card |
—
|
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: IC card | Statement: [Hiroo Station, ticketingMethods, IC card]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ticketingMethods Context triple: [Hiroo Station, ticketingMethods, IC card]
-
A.
ticketPurchaseMethod
Indicates the method or channel through which a ticket was purchased (e.g., online, in person, via mobile app).
-
B.
ticketTypeAccepted
chosen
Indicates that a particular type of ticket is valid for use or accepted in a given context or by a given entity.
-
C.
hasTicketing
Indicates that an entity provides or is associated with a system or mechanism for issuing, managing, or selling tickets.
-
D.
ticketingCompatibleWith
Indicates that two systems, services, or components can interoperate or be used together within the same ticketing or reservation workflow without conflict.
-
E.
ticketingScope
Indicates the range or domain within which ticketing actions (such as creation, assignment, or management of tickets) are valid or applicable.
- 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64146539c8190813debb0d964bc23 |
completed | April 20, 2026, 3:07 p.m. |
| PD | Predicate disambiguation | batch_69e514e941008190898d978d7bde91e4 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:45 p.m.