Triple

T37916947
Position Surface form Disambiguated ID Type / Status
Subject Miami drug cartel E945844 entity
Predicate basedOnRealWorldPhenomenon P93832 FINISHED
Object Miami cocaine trade of the 1980s 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: Miami cocaine trade of the 1980s | Statement: [Miami drug cartel, basedOnRealWorldPhenomenon, Miami cocaine trade of the 1980s]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: basedOnRealWorldPhenomenon
Context triple: [Miami drug cartel, basedOnRealWorldPhenomenon, Miami cocaine trade of the 1980s]
  • A. basedOnRealLife chosen
    Indicates that something is derived from, inspired by, or directly adapted from actual real-world events, people, or situations.
  • B. influencedByRealWorldConcept
    Indicates that something is shaped, inspired, or determined by an existing concept, phenomenon, or principle from the real world.
  • C. hasRealityCounterpartInFiction
    Indicates that a fictional element corresponds to or is based on a real-world counterpart within a work of fiction.
  • D. basedInUniverseOn
    Indicates that something is set or takes place within a fictional universe that is derived from, inspired by, or adapted from another source.
  • E. privateReality
    Indicates that an entity experiences or maintains a subjective, internal version of reality that may differ from shared or objective reality.
  • 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_69ff7bc112088190851501fb2a16103d completed May 9, 2026, 6:24 p.m.
PD Predicate disambiguation batch_69ff7b45507c81909753866ad733601a completed May 9, 2026, 6:21 p.m.
Created at: May 3, 2026, 4:20 p.m.