Triple
T37976457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IRS Form 720 |
E947436
|
entity |
| Predicate | interestRule |
P193950
|
FINISHED |
| Object | interest may accrue on late payments |
—
|
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: interest may accrue on late payments | Statement: [IRS Form 720, interestRule, interest may accrue on late payments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: interestRule Context triple: [IRS Form 720, interestRule, interest may accrue on late payments]
-
A.
interestPolicy
chosen
Indicates the policy or rules governing how interest is calculated, applied, or managed in a given financial context.
-
B.
interestTreatment
Indicates that one entity has an interest in, or is concerned with, a particular treatment or therapeutic intervention.
-
C.
interestType
Indicates the specific category or nature of interest that one entity has in relation to another or to a subject.
-
D.
interestMayBe
Indicates that one entity potentially has an interest in, or may be interested in, another entity or subject.
-
E.
interestRatePolicy
Indicates the relationship in which a governing financial authority sets or adjusts interest rates to influence economic conditions and borrowing costs.
- 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_69f76ef7db908190bba6086673a32300 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fee691952c8190822da83e46311d1d |
completed | May 9, 2026, 7:47 a.m. |
| PD | Predicate disambiguation | batch_69fee62f285c8190a625562a9b80526e |
completed | May 9, 2026, 7:45 a.m. |
Created at: May 3, 2026, 4:20 p.m.