Triple
T37789246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CSRS |
E942035
|
entity |
| Predicate | pensionFormulaBasis |
P6447
|
FINISHED |
| Object | years of service and high-3 average salary |
—
|
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: years of service and high-3 average salary | Statement: [CSRS, pensionFormulaBasis, years of service and high-3 average salary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pensionFormulaBasis Context triple: [CSRS, pensionFormulaBasis, years of service and high-3 average salary]
-
A.
calculationBasis
chosen
Indicates the rule, method, or reference standard used as the foundation for performing a calculation in the relationship.
-
B.
pensionAmount
Indicates the specific monetary value of a pension that is assigned to or received by an entity.
-
C.
pensionEligibility
Indicates that an entity qualifies to receive pension benefits under specified rules or conditions.
-
D.
pensionStartDate
Indicates the date on which a person’s pension benefits begin to accrue or be paid.
-
E.
mainPensionLaw
Indicates that a given law or regulation serves as the primary legal basis governing pension rights or pension systems for 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_69f76ee5cb0c81909a363d1c929156c0 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbb9e8108c8190ae1c7940b1677e95 |
completed | May 6, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fbb141605c8190b9c27d70352522db |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:19 p.m.