Triple
T23207519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cannabis Act |
E580500
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | cannabis law |
C9683
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: cannabis law Context triple: [Cannabis Act, instanceOf, cannabis law]
-
A.
cannabis brand
A cannabis brand is a distinct identity under which cannabis-related products and experiences are marketed, differentiated, and trusted by consumers.
-
B.
drug control policy
chosen
Drug control policy is a framework of laws, regulations, and strategies designed to manage the production, distribution, and use of drugs to protect public health and safety.
-
C.
legalization program
A legalization program is an organized governmental or institutional initiative that formally grants legal status, rights, or protections to previously unauthorized or informal activities, entities, or individuals under defined conditions.
-
D.
anti-drug legislation
Anti-drug legislation comprises laws and regulations designed to control, restrict, or prohibit the production, distribution, possession, and use of certain drugs, often with the goals of protecting public health, reducing crime, and regulating pharmaceutical and recreational substances.
-
E.
American medical cannabis patient
An American medical cannabis patient is an individual in the United States who has received legal authorization from a licensed healthcare provider to use cannabis products for the treatment or management of qualifying medical conditions under state-specific medical marijuana laws.
- F. None of above.
Provenance (1 batch)
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_69e24602ae1481908aaa6bc7ca493867 |
completed | April 17, 2026, 2:38 p.m. |
Created at: April 17, 2026, 4:07 p.m.