Triple
T12372122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AP exams |
E295027
|
entity |
| Predicate | feeReductionAvailable |
P5429
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [AP exams, feeReductionAvailable, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: feeReductionAvailable Context triple: [AP exams, feeReductionAvailable, yes]
-
A.
fareCapping
Indicates a limit on the total amount a rider can be charged for fares over a set period, after which additional trips are free or discounted.
-
B.
fareDiscount
chosen
Indicates that a reduced price is applied to a standard fare for a product or service.
-
C.
tollExemption
Indicates that an entity is not required to pay a toll or fee that would normally be charged for using a particular route, facility, or service.
-
D.
reducedCommissionRate
Indicates that the commission rate applied to a transaction or agreement is lower than the standard or previously agreed rate.
-
E.
fareAppliesTo
Indicates that a specific fare is applicable to a particular trip, service, passenger category, or travel condition.
- 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_69d6ab6d8a4081908636601e69ddf262 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d942a2d6e08190a13c7ff89af09354 |
completed | April 10, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69d93ecf6b548190a394b6b56a0c1c68 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.