Triple
T8362387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delta SkyMiles Blue American Express Card |
E197039
|
entity |
| Predicate | foreignTransactionFeeType |
P37869
|
FINISHED |
| Object | no foreign transaction fees |
—
|
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 foreign transaction fees | Statement: [Delta SkyMiles Blue American Express Card, foreignTransactionFeeType, no foreign transaction fees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foreignTransactionFeeType Context triple: [Delta SkyMiles Blue American Express Card, foreignTransactionFeeType, no foreign transaction fees]
-
A.
feeType
chosen
Indicates the specific category or classification of a fee associated with a transaction, service, or obligation.
-
B.
feeUnit
Indicates the unit of measurement or currency in which a fee amount is expressed.
-
C.
feeTypeAuthorized
Indicates that a particular type of fee is permitted or approved for use in a given context or relationship.
-
D.
feePolicy
Indicates the rules or conditions that determine how fees are calculated, applied, or charged in a given context.
-
E.
fareType
Indicates the category or class of fare (such as standard, discounted, or promotional) that applies to a given trip, ticket, or pricing instance.
- 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.