Triple
T17005074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roth IRA |
E412548
|
entity |
| Predicate | penaltyExceptionsInclude |
P68180
|
FINISHED |
| Object | first-time home purchase |
—
|
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: first-time home purchase | Statement: [Roth IRA, penaltyExceptionsInclude, first-time home purchase]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: penaltyExceptionsInclude Context triple: [Roth IRA, penaltyExceptionsInclude, first-time home purchase]
-
A.
providesExemptionsTo
chosen
Indicates that one entity grants or offers exemptions, waivers, or exceptions from rules, obligations, or requirements to another entity.
-
B.
penaltyRules
Indicates the rules or conditions under which penalties are defined, applied, or enforced in a given context.
-
C.
supportsPenalty
Indicates that one entity endorses, approves of, or is in favor of a particular penalty being applied to another entity or situation.
-
D.
penaltyProvision
Indicates that a rule, contract, or law includes a clause specifying a punishment or sanction for non-compliance or violation.
-
E.
exemptedFrom
Indicates that an entity is not subject to, or is formally released from, a rule, obligation, requirement, or liability that would otherwise apply.
- 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_69d886cb581c8190ab05f4b429c9cd85 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d382400c819092ec0ca0de815888 |
completed | April 18, 2026, 6:54 p.m. |
| PD | Predicate disambiguation | batch_69e35d552bc08190af17ef7659e094ef |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:32 a.m.