Triple
T24483286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Massachusetts College Savings Programs |
E617435
|
entity |
| Predicate | investmentRisk |
P15871
|
FINISHED |
| Object | borne by account owner for investment-based 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: borne by account owner for investment-based plan | Statement: [Massachusetts College Savings Programs, investmentRisk, borne by account owner for investment-based plan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: investmentRisk Context triple: [Massachusetts College Savings Programs, investmentRisk, borne by account owner for investment-based plan]
-
A.
riskBasis
Indicates the underlying factor, condition, or rationale that forms the basis for assessing or assigning risk in a given context.
-
B.
riskType
chosen
Indicates the category or nature of risk associated with an entity, event, or relationship.
-
C.
risk
Indicates that one entity is exposed or subject to potential harm, loss, or adverse outcome arising from another entity, action, or situation.
-
D.
riskSensitivity
Indicates how strongly an entity’s decisions or behavior change in response to potential risk or uncertainty.
-
E.
riskLevel
Indicates the degree of potential harm, loss, or adverse outcome associated with a particular situation, action, or entity.
- 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_69e2d7f3ae788190b683394db15f220e |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2a9d912e88190bc39c05a9d7f407e |
completed | April 30, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69f2a6a4580481908fddc385f5262f95 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:21 a.m.