Triple
T5544316
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Small Business Act of 1958 |
E145368
|
entity |
| Predicate | createsProgramType |
P2192
|
FINISHED |
| Object | federal small business loan programs |
—
|
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 small business loan programs | Statement: [Small Business Act of 1958, createsProgramType, federal small business loan programs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createsProgramType Context triple: [Small Business Act of 1958, createsProgramType, federal small business loan programs]
-
A.
createdProgram
Indicates that an entity authored, developed, or produced a particular program (such as software or a coded application).
-
B.
componentProgram
Indicates that one entity is a component or module that forms part of a larger program or software system represented by the other entity.
-
C.
madeProgram
Indicates that one entity created, developed, or authored a program (such as software or a coded application).
-
D.
programType
chosen
Indicates the category or kind of program to which an entity belongs or with which it is associated.
-
E.
creationType
Indicates the manner or process by which something was brought into existence or produced.
- 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_69c008fa64888190adae56c8f9ea4031 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01fcad7d88190b83bb4ecb3b34bfd |
completed | March 22, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69c01b0e72f08190bf705d8fe1639401 |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:35 p.m.