Triple
T28249755
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delta Air Lines loyalty program |
E712280
|
entity |
| Predicate | milesCanBeRedeemedFor |
P110533
|
FINISHED |
| Object | flights |
—
|
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: flights | Statement: [Delta Air Lines loyalty program, milesCanBeRedeemedFor, flights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: milesCanBeRedeemedFor Context triple: [Delta Air Lines loyalty program, milesCanBeRedeemedFor, flights]
-
A.
canBeRedeemedFor
chosen
Indicates that one item, asset, or benefit may be exchanged or converted to obtain another specified item, asset, or benefit.
-
B.
milesCanBePurchased
Indicates that a certain number of miles are eligible to be bought, typically in exchange for money or points.
-
C.
mileageAccrual
Indicates the accumulation or earning of mileage (such as distance-based points or credits) as a result of certain actions or usage.
-
D.
mileEarningUnit
Indicates the unit or basis (e.g., per mile, per dollar) used to calculate or award mileage or points in a mileage-earning relationship.
-
E.
canBeRebatedTo
Indicates that a cost, fee, or amount is eligible to be refunded or credited back to a specified party.
- 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_69efb51fb98881909692421959ec0170 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f643ee1a1881909a7f4588daba8eca |
completed | May 2, 2026, 6:35 p.m. |
| PD | Predicate disambiguation | batch_69f641e0fde08190bf06a1c5b388aa84 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 11:03 p.m.