Triple
T21170091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prime Student |
E521667
|
entity |
| Predicate | discountedFrom |
P100188
|
FINISHED |
| Object | standard Amazon Prime membership |
—
|
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: standard Amazon Prime membership | Statement: [Prime Student, discountedFrom, standard Amazon Prime membership]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: discountedFrom Context triple: [Prime Student, discountedFrom, standard Amazon Prime membership]
-
A.
discountRate
Indicates the percentage or amount by which a price, cost, or value is reduced relative to its original level.
-
B.
discountMechanism
chosen
Indicates a relationship where one entity defines the method, rule, or process by which a discount is calculated, applied, or granted to another entity.
-
C.
usesDiscountFactor
Indicates that an entity applies a discount factor when evaluating or calculating the value of something over time or across scenarios.
-
D.
fareDiscount
Indicates that a reduced price is applied to a standard fare for a product or service.
-
E.
reducedCommissionRate
Indicates that the commission rate applied to a transaction or agreement is lower than the standard or previously agreed rate.
- 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_69e0b50e30748190b186824a206d39b9 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72711be9481909f16107b71d3500a |
completed | April 21, 2026, 7:28 a.m. |
| PD | Predicate disambiguation | batch_69e5f6027c248190a170a36612bd337e |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3 p.m.