Triple
T31692114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rhode Island Turnpike and Bridge Authority |
E808819
|
entity |
| Predicate | appliesTollingSystem |
P73181
|
FINISHED |
| Object | electronic toll collection |
—
|
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: electronic toll collection | Statement: [Rhode Island Turnpike and Bridge Authority, appliesTollingSystem, electronic toll collection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesTollingSystem Context triple: [Rhode Island Turnpike and Bridge Authority, appliesTollingSystem, electronic toll collection]
-
A.
appliesTollTo
Indicates that a fee or charge is imposed on a subject for using, accessing, or passing through something.
-
B.
operatesTollSystem
Indicates that an entity is responsible for running and managing a toll collection system.
-
C.
tollingType
Indicates the specific method or basis by which a toll, fee, or charge is applied or calculated in a given context.
-
D.
typeOfTollSystem
chosen
Indicates the specific kind or category of toll collection system used in a given context.
-
E.
hasTollCollectionRole
Indicates that an entity participates in toll collection with a specified functional role (e.g., operator, collector, or managing authority).
- 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_69f348ddcbc48190950cabcc25ff29b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fe6fea4a288190bf8615c5d6bf41b4 |
completed | May 8, 2026, 11:21 p.m. |
| PD | Predicate disambiguation | batch_69fe6f774de08190975a2393b9a1fd22 |
completed | May 8, 2026, 11:19 p.m. |
Created at: April 30, 2026, 11:09 p.m.