Triple
T8362377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delta SkyMiles Blue American Express Card |
E197039
|
entity |
| Predicate | annualFeeType |
P37869
|
FINISHED |
| Object | no annual fee |
—
|
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: no annual fee | Statement: [Delta SkyMiles Blue American Express Card, annualFeeType, no annual fee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: annualFeeType Context triple: [Delta SkyMiles Blue American Express Card, annualFeeType, no annual fee]
-
A.
feeType
chosen
Indicates the specific category or classification of a fee associated with a transaction, service, or obligation.
-
B.
isAnnual
Indicates that something occurs, is scheduled, or is valid once every year.
-
C.
chargesMembershipFee
Indicates that an entity requires another entity to pay a membership fee in order to access its services, benefits, or participation.
-
D.
annualFrom
Indicates that something recurs or is calculated on a yearly basis starting from a specified point in time.
-
E.
chargeType
Indicates the category or nature of a charge applied in a transaction or interaction between entities (e.g., fee type, billing classification, or legal charge type).
- 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_69ca82f2dbe48190aba982e75a0d94de |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb8074e4588190b394d1622adca2cb |
completed | March 31, 2026, 8:06 a.m. |
| PD | Predicate disambiguation | batch_69cb70ca25548190b0f90c5384e3fb3c |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6 p.m.