Triple
T19524224
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Riga bus lines |
E488478
|
entity |
| Predicate | fareDiscountsFor |
P31871
|
FINISHED |
| Object | students |
—
|
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: students | Statement: [Riga bus lines, fareDiscountsFor, students]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fareDiscountsFor Context triple: [Riga bus lines, fareDiscountsFor, students]
-
A.
fareDiscount
Indicates that a reduced price is applied to a standard fare for a product or service.
-
B.
fareAppliesTo
chosen
Indicates that a specific fare is applicable to a particular trip, service, passenger category, or travel condition.
-
C.
discountRate
Indicates the percentage or amount by which a price, cost, or value is reduced relative to its original level.
-
D.
offersDiscountsOn
Indicates that one entity provides price reductions or special discount deals specifically applied to another entity or its associated items or services.
-
E.
discountMechanism
Indicates a relationship where one entity defines the method, rule, or process by which a discount is calculated, applied, or granted to another entity.
- 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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e636392444819094f6a2aa1cdf3d42 |
completed | April 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:41 p.m.