Triple
T4960141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RATP bus network |
E111384
|
entity |
| Predicate | primaryTicketingSystem |
P61444
|
FINISHED |
| Object | Île-de-France Mobilités fare system |
—
|
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: Île-de-France Mobilités fare system | Statement: [RATP bus network, primaryTicketingSystem, Île-de-France Mobilités fare system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryTicketingSystem Context triple: [RATP bus network, primaryTicketingSystem, Île-de-France Mobilités fare system]
-
A.
ticketSystem
Indicates a relationship where an entity is managed, tracked, or processed through a ticket-based system for handling requests, issues, or tasks.
-
B.
primaryTerminalFor
Indicates that one entity serves as the main or principal terminal associated with another entity.
-
C.
primaryService
Indicates that one entity serves as the main or principal service provided or used in relation to another entity.
-
D.
primaryBus
Indicates that one entity functions as the main or principal bus associated with another entity within a system or configuration.
-
E.
primaryTenantTo
Indicates that one entity serves as the main or principal tenant in relation to another entity, such as a property or lease.
- F. None of above. chosen
Provenance (4 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_69bd4419393c819086319a6fe4bf8542 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd72e49b048190bac55d9e7a6f7963 |
completed | March 20, 2026, 4:16 p.m. |
| PD | Predicate disambiguation | batch_69bd71447fe88190bb62c5e8753da7a7 |
completed | March 20, 2026, 4:09 p.m. |
| PDg | Predicate description generation | batch_69bd72e1b7cc8190b2e621fdf8f22e38 |
completed | March 20, 2026, 4:16 p.m. |
Created at: March 20, 2026, 1:32 p.m.