Triple
T27175557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Carolina 401(k) and 457 retirement savings plans |
E683033
|
entity |
| Predicate | withdrawalEvent |
P161936
|
FINISHED |
| Object | separation from 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: separation from service | Statement: [North Carolina 401(k) and 457 retirement savings plans, withdrawalEvent, separation from service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: withdrawalEvent Context triple: [North Carolina 401(k) and 457 retirement savings plans, withdrawalEvent, separation from service]
-
A.
withdrawalEvent
chosen
Indicates an event in which something (typically money or resources) is taken out or removed from an account, location, or system.
-
B.
withdrawalBegan
Indicates that the process of withdrawing or removing something from a source has started.
-
C.
withdrawalEnd
Indicates the point in time or condition at which a withdrawal process or right comes to an end.
-
D.
withdrawnDuring
Indicates that something is removed, canceled, or taken back over the course of a specified time period or event.
-
E.
withdrawalType
Indicates the specific method or category by which a withdrawal is carried out in a given context.
- 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_69eefad086808190ab89816c0c300476 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f62579073c8190af7e10be70f2379d |
completed | May 2, 2026, 4:25 p.m. |
| PD | Predicate disambiguation | batch_69f620e38aec8190bb184edcdbd6da64 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 9:25 a.m.