Triple
T11712366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Civil Service Retirement System |
E278402
|
entity |
| Predicate | benefitFormulaBasedOn |
P55857
|
FINISHED |
| Object | years of creditable service |
—
|
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 creditable service | Statement: [Civil Service Retirement System, benefitFormulaBasedOn, years of creditable service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: benefitFormulaBasedOn Context triple: [Civil Service Retirement System, benefitFormulaBasedOn, years of creditable service]
-
A.
benefitStructure
Indicates a relationship where one entity defines, organizes, or governs the benefits (such as advantages, compensations, or perks) provided to or associated with another entity.
-
B.
criterionForBenefits
chosen
Indicates that something serves as a condition or standard that must be met in order for an entity to receive certain benefits.
-
C.
hasBenefit
Indicates that one entity provides an advantage, improvement, or positive outcome to another entity.
-
D.
benefitForm
Indicates that one entity is a specific form, type, or variant in which a benefit is provided or realized for another entity.
-
E.
benefitsAre
Indicates that certain advantages, gains, or positive outcomes are possessed by or accrue to a particular entity or group.
- 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_69d6aaff2ce88190b4a1e4b341ad5377 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4be10088190854699385d1f6a95 |
completed | April 10, 2026, 7:20 a.m. |
| PD | Predicate disambiguation | batch_69d88a7d483081909c2a101087515d74 |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:40 p.m.