Triple
T38267021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stockholm congestion tax |
E1021091
|
entity |
| Predicate | chargingPrinciple |
P96151
|
FINISHED |
| Object | cordon-based charge |
—
|
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: cordon-based charge | Statement: [Stockholm congestion tax, chargingPrinciple, cordon-based charge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chargingPrinciple Context triple: [Stockholm congestion tax, chargingPrinciple, cordon-based charge]
-
A.
chargingModel
chosen
Indicates the pricing or billing scheme applied to an entity, such as how costs are calculated or charged.
-
B.
charging
Indicates that one entity is supplying electrical energy to another entity’s battery or power storage system.
-
C.
chargingInterface
Indicates that one entity serves as a power/energy charging connection or port used by another entity.
-
D.
chargeStoredProportionalTo
Indicates that the amount of charge stored in one entity varies in direct proportion to a specified quantity or property of another entity.
-
E.
chargingBranding
Indicates a relationship where one entity is responsible for the branding or brand identity associated with a charging service, product, or infrastructure.
- 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_69f76dee198c8190bf5109421e47a658 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fcc3321ef081908023590ba70ba0cf |
completed | May 7, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69fcb0fdc6e08190b05e894c59481a0d |
completed | May 7, 2026, 3:34 p.m. |
Created at: May 3, 2026, 4:30 p.m.