Triple
T8168111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delta SkyMiles Platinum American Express Card |
E190745
|
entity |
| Predicate | cardTier |
P81062
|
FINISHED |
| Object | mid-tier |
—
|
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: mid-tier | Statement: [Delta SkyMiles Platinum American Express Card, cardTier, mid-tier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cardTier Context triple: [Delta SkyMiles Platinum American Express Card, cardTier, mid-tier]
-
A.
cardType
Indicates the classification or category assigned to a card within a given system or context.
-
B.
cardFormat
Indicates the specific layout or structural style in which a card or card-like item is presented or encoded.
-
C.
cardFunction
Indicates that one entity serves as the functional role, capability, or purpose associated with a card-related entity in a system.
-
D.
cardNetworkRank
Indicates the relative position or ranking of a payment card network compared to other card networks, typically based on metrics such as usage, market share, or performance.
-
E.
loyaltyProgramTierOf
Indicates the specific loyalty or rewards program tier that an entity (such as a customer or account) belongs to.
- F. None of above. chosen
Provenance (4 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_69ca82c0ef14819083713f4473dd847c |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb46698fb88190a6d520b05cb9b03e |
completed | March 31, 2026, 3:58 a.m. |
| PD | Predicate disambiguation | batch_69cb36a4c40c81909f60aef0e1624c13 |
completed | March 31, 2026, 2:51 a.m. |
| PDg | Predicate description generation | batch_69cb40a017608190b6b48cf60335fa8d |
completed | March 31, 2026, 3:33 a.m. |
Created at: March 30, 2026, 5:39 p.m.