Triple
T20125730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fentanyl |
E490748
|
entity |
| Predicate | illicitForm |
P109009
|
FINISHED |
| Object | counterfeit tablets |
—
|
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: counterfeit tablets | Statement: [Fentanyl, illicitForm, counterfeit tablets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: illicitForm Context triple: [Fentanyl, illicitForm, counterfeit tablets]
-
A.
circulatedIllegallyIn
chosen
Indicates that something was distributed or shared within a particular place or context in violation of laws or regulations.
-
B.
illegalMarket
Indicates a market relationship where goods or services are traded in violation of laws or regulations.
-
C.
primaryIllegalCommodity
Indicates that the referenced commodity is the main or most significant illegal good involved in an activity, transaction, or case.
-
D.
protestForm
Indicates the specific method or mode by which a protest or demonstration is carried out.
-
E.
isCriminalizedIn
Indicates that a specific behavior, action, or condition is prohibited and subject to legal penalties within a particular jurisdiction or legal system.
- 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6674223008190827c454fe7ac86f4 |
completed | April 20, 2026, 5:49 p.m. |
| PD | Predicate disambiguation | batch_69e54cfb0d0081908e789b9b57e96668 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:31 p.m.