Triple
T2371736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oregon 529 college savings programs |
E46103
|
entity |
| Predicate | feeType |
P37869
|
FINISHED |
| Object | program management fees |
—
|
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: program management fees | Statement: [Oregon 529 college savings programs, feeType, program management fees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: feeType Context triple: [Oregon 529 college savings programs, feeType, program management fees]
-
A.
fareType
Indicates the category or class of fare (such as standard, discounted, or promotional) that applies to a given trip, ticket, or pricing instance.
-
B.
feePolicy
Indicates the rules or conditions that determine how fees are calculated, applied, or charged in a given context.
-
C.
fareTypes
Indicates the categories or kinds of fares (e.g., ticket or pricing options) that apply to a given travel or service offering.
-
D.
fareStructure
Indicates the pricing scheme or set of rules that determine how fares are calculated and applied for a given service or trip.
-
E.
feeTypeAuthorized
Indicates that a particular type of fee is permitted or approved for use in a given context or relationship.
- F. None of above. chosen
Provenance (4 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc771302481908540e31abb5aeeba |
completed | March 7, 2026, 6:36 a.m. |
| PD | Predicate disambiguation | batch_69abc59b88348190a2d6c08f69974117 |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abc6443c6c8190b932de2abd8eb28f |
completed | March 7, 2026, 6:31 a.m. |
Created at: March 4, 2026, 7:56 p.m.