Triple
T7940003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amazon Elastic Kubernetes Service |
E184364
|
entity |
| Predicate | billingComponent |
P55566
|
FINISHED |
| Object | per-cluster control plane fee |
—
|
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: per-cluster control plane fee | Statement: [Amazon Elastic Kubernetes Service, billingComponent, per-cluster control plane fee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: billingComponent Context triple: [Amazon Elastic Kubernetes Service, billingComponent, per-cluster control plane fee]
-
A.
billing
Indicates that one entity charges another entity for goods or services, typically by issuing an invoice or request for payment.
-
B.
billingMetric
Indicates a relationship where a specific metric or measure is used as the basis for calculating billing or charges between entities.
-
C.
chargeDetail
chosen
Indicates a detailed specification of a financial charge, including its components, conditions, or breakdown within a transaction or billing context.
-
D.
billingMethod
Indicates the way in which payment is arranged, processed, or charged for a product, service, or account.
-
E.
billColor
Indicates the color attribute associated with the bill (beak) of an entity.
- 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_69ca8290c21c8190906a5ca6fe2b03c4 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3b0983388190a77e8d5d899c5130 |
completed | March 31, 2026, 3:10 a.m. |
| PD | Predicate disambiguation | batch_69cae93526d081909303265bf60419fd |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:08 p.m.