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.