Triple
T37657932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Azure Savings Plan for Compute |
E937646
|
entity |
| Predicate | supportsBillingType |
P97754
|
FINISHED |
| Object | Enterprise Agreement |
—
|
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: Enterprise Agreement | Statement: [Azure Savings Plan for Compute, supportsBillingType, Enterprise Agreement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsBillingType Context triple: [Azure Savings Plan for Compute, supportsBillingType, Enterprise Agreement]
-
A.
hasStarBilling
Indicates that an entity is given top or prominently featured billing in a production or presentation.
-
B.
usesBillingModel
chosen
Indicates that one entity applies or operates under a particular billing model for charging or pricing purposes.
-
C.
supportsAccountType
Indicates that one entity is compatible with, or able to operate for, a specified type or category of account.
-
D.
supportsCodeRates
Indicates that one entity is capable of handling, processing, or operating at the specific code rates associated with another entity.
-
E.
supportsSettlementType
Indicates that one entity is capable of accommodating, enabling, or being suitable for a particular type or category of settlement.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1772e48190ba738c6d11b321e2 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:18 p.m.