Triple
T24197781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Medellín Cartel |
E599881
|
entity |
| Predicate | primaryIllicitProduct |
P56589
|
FINISHED |
| Object | cocaine |
—
|
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: cocaine | Statement: [Medellín Cartel, primaryIllicitProduct, cocaine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryIllicitProduct Context triple: [Medellín Cartel, primaryIllicitProduct, cocaine]
-
A.
primaryIllegalCommodity
chosen
Indicates that the referenced commodity is the main or most significant illegal good involved in an activity, transaction, or case.
-
B.
typeOfDrugsTrafficked
Indicates that one entity specifies the category or kind of drugs that are being trafficked in the context of a drug-trafficking activity.
-
C.
legalStatusOfItems
Indicates the legal classification or regulatory standing that applies to specified items.
-
D.
drugPolicy
Indicates the rules, regulations, or guidelines governing the use, control, or management of drugs within a given context.
-
E.
primarySubstanceExample
Indicates that one entity serves as the main illustrative example of a particular substance associated with another entity.
- 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_69e288ceaab88190899d0acb5931591d |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1e24c103481908ea49dd8e77dee32 |
completed | April 29, 2026, 10:49 a.m. |
| PD | Predicate disambiguation | batch_69f1c43e55688190b55fc20274ed471c |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:36 p.m.