Triple
T9800805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple Card |
E237830
|
entity |
| Predicate | cashBackRate |
P57184
|
FINISHED |
| Object | 3% at Apple purchases |
—
|
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: 3% at Apple purchases | Statement: [Apple Card, cashBackRate, 3% at Apple purchases]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cashBackRate Context triple: [Apple Card, cashBackRate, 3% at Apple purchases]
-
A.
discountRate
Indicates the percentage or amount by which a price, cost, or value is reduced relative to its original level.
-
B.
loyaltyIncentive
chosen
Indicates a relationship where benefits or rewards are provided to encourage or recognize continued commitment or repeat engagement.
-
C.
campaignCredit
Indicates that credit or attribution for a campaign’s outcome, performance, or impact is assigned to a particular entity.
-
D.
rechargeRate
Indicates the rate or speed at which something restores or replenishes its capacity, energy, or resources over time.
-
E.
commissionRateRevertsTo
Indicates that a previously modified commission rate returns to an earlier or default commission 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_69ca84dd4608819097ff4ed00feca280 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda62a11a88190880e0cce24923b14 |
completed | April 1, 2026, 11:11 p.m. |
| PD | Predicate disambiguation | batch_69cd03da45a88190b71b1be3354c15a6 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:29 p.m.