Triple
T1684507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Main Cabin (Delta Air Lines) |
E36411
|
entity |
| Predicate | earns |
P30192
|
FINISHED |
| Object | SkyMiles award miles |
—
|
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: SkyMiles award miles | Statement: [Main Cabin (Delta Air Lines), earns, SkyMiles award miles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earns Context triple: [Main Cabin (Delta Air Lines), earns, SkyMiles award miles]
-
A.
earnOn
chosen
Indicates that one entity gains income, profit, or returns as a result of another entity or activity.
-
B.
salary
Indicates the amount of monetary compensation an entity receives, typically on a regular basis, for work or services performed.
-
C.
pays
Indicates that one entity gives money or another form of compensation to another entity, typically in exchange for goods, services, or to settle a debt.
-
D.
vests
Indicates that legal rights, ownership, or authority are conferred upon and secured in a person or entity, often becoming fully effective at a specific time or upon certain conditions.
-
E.
incomeType
Indicates the category or source classification of an entity’s income within a given context.
- 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_69a886151508819084fa7f1ce6e05577 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aba644070c81908745b56d981fe273 |
completed | March 7, 2026, 4:15 a.m. |
| PD | Predicate disambiguation | batch_69aa61b57a6881909373af287ef24799 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:29 p.m.