Triple
T17005602
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hero Miles program |
E412561
|
entity |
| Predicate | costToBeneficiaries |
P5902
|
FINISHED |
| Object | no cost for airline tickets |
—
|
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 cost for airline tickets | Statement: [Hero Miles program, costToBeneficiaries, no cost for airline tickets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: costToBeneficiaries Context triple: [Hero Miles program, costToBeneficiaries, no cost for airline tickets]
-
A.
costToUser
chosen
Indicates the amount of cost or expense that is borne by, charged to, or incurred by the user.
-
B.
beneficiaries
Indicates that certain entities receive advantages, profits, or positive outcomes from an action, event, or arrangement.
-
C.
costSharing
Indicates how the financial burden of a cost is divided or shared among multiple parties.
-
D.
costsProvision
Indicates that providing a particular good, service, or resource requires incurring a specified cost.
-
E.
estimatedNumberOfBeneficiaries
Indicates the approximate count of individuals or entities expected to receive benefits from something.
- 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_69d886cb581c8190ab05f4b429c9cd85 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d382400c819092ec0ca0de815888 |
completed | April 18, 2026, 6:54 p.m. |
| PD | Predicate disambiguation | batch_69e35d552bc08190af17ef7659e094ef |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:32 a.m.