Triple
T3173993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Subchapter J |
E66417
|
entity |
| Predicate | primaryTaxType |
P3166
|
FINISHED |
| Object | federal income tax |
—
|
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: federal income tax | Statement: [Subchapter J, primaryTaxType, federal income tax]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryTaxType Context triple: [Subchapter J, primaryTaxType, federal income tax]
-
A.
taxType
chosen
Indicates the specific category or classification of tax that applies to an entity, transaction, or amount.
-
B.
primaryType
Indicates the main or most fundamental category or classification assigned to an entity, distinguishing it from any secondary or auxiliary types.
-
C.
typeOfTaxpayerCovered
Indicates the category or kind of taxpayer to which a particular rule, obligation, or provision applies.
-
D.
taxationMethod
Indicates the specific way or system by which taxes are calculated, collected, or applied in a given context.
-
E.
taxRegime
Indicates the system or structure of taxation that governs how taxes are assessed, collected, and applied within a particular context or jurisdiction.
- 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada670c800819098937783e2b05c7a |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0076b4819094628f1ad10b8f68 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.