Triple
T36573228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Postal Life Insurance |
E902171
|
entity |
| Predicate | premiumPaymentMode |
P36173
|
FINISHED |
| Object | salary deduction for eligible employees |
—
|
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: salary deduction for eligible employees | Statement: [Postal Life Insurance, premiumPaymentMode, salary deduction for eligible employees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: premiumPaymentMode Context triple: [Postal Life Insurance, premiumPaymentMode, salary deduction for eligible employees]
-
A.
payType
Indicates the method or category of payment used in a transaction or compensation arrangement.
-
B.
paymentMethod
Indicates the means or instrument through which a payment is made in a transaction.
-
C.
billingMethod
chosen
Indicates the way in which payment is arranged, processed, or charged for a product, service, or account.
-
D.
paymentFunction
Indicates a relationship where one entity defines or performs the method, rules, or process by which payments are calculated, initiated, or executed for another entity or transaction.
-
E.
payerType
Indicates the type or category of entity responsible for making a payment in the relationship.
- 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_69f76e6416708190a9754b8c52d4e453 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1baf25c8190a78dd54a400d2c50 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:11 p.m.