Triple
T34453496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Transdev Rouen |
E884438
|
entity |
| Predicate | operatesPublicTransportContract |
P111896
|
FINISHED |
| Object | Rouen urban network concession |
—
|
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: Rouen urban network concession | Statement: [Transdev Rouen, operatesPublicTransportContract, Rouen urban network concession]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesPublicTransportContract Context triple: [Transdev Rouen, operatesPublicTransportContract, Rouen urban network concession]
-
A.
operatesTransitSystem
Indicates that one entity manages and runs the public transportation network or services for another entity or area.
-
B.
publicTransportOperatorFor
chosen
Indicates that one entity operates or manages public transportation services for another entity or area.
-
C.
transitSystemTypeOperated
Indicates the type of transit system that an operator runs or manages.
-
D.
operatedPassengerServices
Indicates that an entity provided and managed transportation services specifically for carrying passengers.
-
E.
hasPublicTransportAgency
Indicates that a place or transport system is served, managed, or overseen by a specific public transportation agency.
- 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_69f349c607688190b553539d14901a35 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a00b479c1588190af6e0698b7f8d7f7 |
completed | May 10, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_6a00b4158260819087d0cfad8b18cef4 |
completed | May 10, 2026, 4:36 p.m. |
Created at: May 1, 2026, 2 a.m.