Triple
T37916956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miami drug cartel |
E945844
|
entity |
| Predicate | importRoute |
P61117
|
FINISHED |
| Object | from Latin America to Miami |
—
|
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: from Latin America to Miami | Statement: [Miami drug cartel, importRoute, from Latin America to Miami]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: importRoute Context triple: [Miami drug cartel, importRoute, from Latin America to Miami]
-
A.
exportRoute
chosen
Indicates the route or pathway through which goods, services, or data are exported from one location or entity to another.
-
B.
routeUnder
Indicates that one route passes beneath another route or structure, typically at an underpass or similar crossing.
-
C.
coreRouteOf
Indicates that one entity serves as the primary or central route associated with another entity (such as a network, service, or system).
-
D.
exampleRoute
Indicates a route that serves as a representative or illustrative path among possible routes between locations.
-
E.
routingSystem
Indicates a relationship where an entity functions as or is associated with a system that determines and manages the paths or routes taken between points.
- 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_69f76ef2ebd88190be5229f2621070b3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc995dc2481908b3bd4217f8101e7 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.