Triple
T33371607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Capital One Savor Rewards Card |
E854504
|
entity |
| Predicate | introBonus |
P193848
|
FINISHED |
| Object | may offer sign-up bonus |
—
|
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: may offer sign-up bonus | Statement: [Capital One Savor Rewards Card, introBonus, may offer sign-up bonus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: introBonus Context triple: [Capital One Savor Rewards Card, introBonus, may offer sign-up bonus]
-
A.
hasSignUpBonus
chosen
Indicates that an entity offers or is associated with a promotional bonus granted upon signing up or registering.
-
B.
supportsBonus
Indicates that one entity provides or enables an additional benefit, reward, or bonus for another entity.
-
C.
hasIntro
Indicates that an entity includes or is associated with an introductory section or opening part.
-
D.
bonusCategory
Indicates the classification or type of bonus associated with an entity or transaction.
-
E.
offersIncentive
Indicates that one entity provides a reward, benefit, or motivation to another entity to encourage a specific action or behavior.
- 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_69f3496bda8c8190bfc8fade9d1b791c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fdb04ed81c8190b8feea90c1c785a6 |
completed | May 8, 2026, 9:43 a.m. |
| PD | Predicate disambiguation | batch_69fda9d6c5148190a63205b6d9b0a1b4 |
completed | May 8, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:35 a.m.