Triple
T26554101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CalSTRS Cash Balance Benefit Program |
E671755
|
entity |
| Predicate | planSponsorCategory |
P124629
|
FINISHED |
| Object | county offices of education |
—
|
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: county offices of education | Statement: [CalSTRS Cash Balance Benefit Program, planSponsorCategory, county offices of education]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: planSponsorCategory Context triple: [CalSTRS Cash Balance Benefit Program, planSponsorCategory, county offices of education]
-
A.
sponsorCategoryName
chosen
Indicates the classification label or category assigned to a sponsor in a given context.
-
B.
sponsoringOrganizationType
Indicates the kind or category of organization that provides sponsorship or support in the described relationship or activity.
-
C.
coSponsor
Indicates that an entity jointly supports, endorses, or backs an initiative, proposal, or activity together with one or more others.
-
D.
sponsorType
Indicates the specific role or category of sponsorship that an entity provides in relation to another entity or event.
-
E.
sponsoredPrograms
Indicates that an entity provides financial or resource support to specific programs or initiatives.
- 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_69eeb32163f08190af5f81282738e27a |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61a17a7788190946f7e32d63cd43f |
completed | May 2, 2026, 3:36 p.m. |
| PD | Predicate disambiguation | batch_69f611ab768c8190b1849c15a3e59dda |
completed | May 2, 2026, 3 p.m. |
Created at: April 27, 2026, 1:49 a.m.