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.