Triple
T10561360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troika card |
E249223
|
entity |
| Predicate | supportsTariff |
P70522
|
FINISHED |
| Object | pay-per-ride fares |
—
|
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: pay-per-ride fares | Statement: [Troika card, supportsTariff, pay-per-ride fares]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsTariff Context triple: [Troika card, supportsTariff, pay-per-ride fares]
-
A.
usesTariffSystem
chosen
Indicates that one entity applies or operates under a tariff-based system for pricing, taxation, or fees in its interactions or transactions.
-
B.
supportsCodeRates
Indicates that one entity is capable of handling, processing, or operating at the specific code rates associated with another entity.
-
C.
supportsValue
Indicates that one entity provides justification, evidence, or backing for the truth, relevance, or appropriateness of a particular value associated with another entity.
-
D.
supportsBonus
Indicates that one entity provides or enables an additional benefit, reward, or bonus for another entity.
-
E.
supportsPolicy
Indicates that one entity endorses, backs, or is in favor of a particular policy or set of policies.
- 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d52720621c8190a1126268ebe57c83 |
completed | April 7, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69d51901ff6c819095e7b528170a69dc |
completed | April 7, 2026, 2:47 p.m. |
Created at: April 6, 2026, 12:35 p.m.