Triple
T10998132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MFS 529 Savings Plan |
E259934
|
entity |
| Predicate | qualifiedPlanType |
P8653
|
FINISHED |
| Object | Section 529 plan |
—
|
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: Section 529 plan | Statement: [MFS 529 Savings Plan, qualifiedPlanType, Section 529 plan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: qualifiedPlanType Context triple: [MFS 529 Savings Plan, qualifiedPlanType, Section 529 plan]
-
A.
insuranceType
Indicates the specific category or kind of insurance coverage associated with an entity or relationship.
-
B.
benefitAdministered
Indicates that a benefit (such as aid, service, or entitlement) has been formally provided or delivered to an eligible recipient by an administering party.
-
C.
planType
chosen
Indicates the specific category or kind of plan associated with an entity, such as its level, structure, or intended use.
-
D.
healthcareType
Indicates the category or kind of healthcare service, system, or coverage associated with an entity.
-
E.
awardedForCoverageType
Indicates that something (such as an award, benefit, or recognition) is granted specifically in relation to a particular type or category of coverage.
- 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_69d6aa8a6a548190a750f944ccdc8064 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d796d3b08c81909376cd73c42fcefe |
completed | April 9, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69d72e93ac648190b46c5d12bf3eb1e9 |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:24 p.m.