Triple
T24197826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Medellín Cartel |
E599881
|
entity |
| Predicate | estimatedPeakRevenue |
P7218
|
FINISHED |
| Object | billions of US dollars per year |
—
|
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: billions of US dollars per year | Statement: [Medellín Cartel, estimatedPeakRevenue, billions of US dollars per year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estimatedPeakRevenue Context triple: [Medellín Cartel, estimatedPeakRevenue, billions of US dollars per year]
-
A.
revenueLevel
Indicates the relative amount or tier of revenue associated with an entity or activity.
-
B.
revenue
chosen
Indicates the amount of income generated by an entity from its business activities or operations over a specified period.
-
C.
revenuePaidTo
Indicates that a specified amount of revenue is paid or transferred from one entity to another as a recipient.
-
D.
revenueUse
Indicates how generated revenue is allocated, spent, or applied toward specific purposes or activities.
-
E.
estimatedCost
Indicates the predicted or calculated monetary amount expected to be required for something, such as a project, item, or action.
- 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.