Triple
T12412704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blair v. Commissioner |
E296555
|
entity |
| Predicate | typeOfIncome |
P24934
|
FINISHED |
| Object | trust income |
—
|
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: trust income | Statement: [Blair v. Commissioner, typeOfIncome, trust income]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfIncome Context triple: [Blair v. Commissioner, typeOfIncome, trust income]
-
A.
incomeType
chosen
Indicates the category or source classification of an entity’s income within a given context.
-
B.
income
Indicates the amount of money an entity receives, typically over a specified period, from work, investments, or other sources.
-
C.
salaryType
Indicates the classification or structure of compensation associated with an entity, such as whether pay is salaried, hourly, commission-based, or another type.
-
D.
incomeTreatment
Indicates a relationship where an entity receives, is subject to, or is affected by a particular income-related treatment, policy, or classification.
-
E.
employmentType
Indicates the specific kind or category of employment relationship that exists between an individual and an employer (e.g., full-time, part-time, contract).
- 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_69d6ad9f464c81909db36d7e96e34b9e |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94e1888b48190bd750f839a26e99e |
completed | April 10, 2026, 7:23 p.m. |
| PD | Predicate disambiguation | batch_69d94d354b488190adc83fb4f2770dd5 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.