Triple

T26011357
Position Surface form Disambiguated ID Type / Status
Subject Carlos Lehder E646908 entity
Predicate usedBaseOfOperations P32483 FINISHED
Object Norman's Cay, Bahamas
Norman's Cay, Bahamas is a small island in the Exumas that became infamous in the late 1970s and early 1980s as a major hub for cocaine trafficking in the Caribbean.
 E1703997 NE FINISHED

How this triple was built (3 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: Norman's Cay, Bahamas | Statement: [Carlos Lehder, usedBaseOfOperations, Norman's Cay, Bahamas]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Norman's Cay, Bahamas
Triple: [Carlos Lehder, usedBaseOfOperations, Norman's Cay, Bahamas]
Generated description
Norman's Cay, Bahamas is a small island in the Exumas that became infamous in the late 1970s and early 1980s as a major hub for cocaine trafficking in the Caribbean.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: usedBaseOfOperations
Context triple: [Carlos Lehder, usedBaseOfOperations, Norman's Cay, Bahamas]
  • A. hasBaseOfOperations chosen
    Indicates that an entity uses a particular location as its primary place of operation or activity.
  • B. usedLogisticalBase
    Indicates that one entity employed another entity as a logistical base or hub to support its operations or activities.
  • C. usesAirbase
    Indicates that one entity operates from, accesses, or conducts activities at a particular airbase.
  • D. operatesBase
    Indicates that an organization or agent runs or manages a primary facility, location, or base of operations.
  • E. militaryBaseUser
    Indicates that one entity uses, operates, or is stationed at a particular military base.
  • F. None of above.

Provenance (6 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_69e77e89d5848190b54352cdb74f6029 completed April 21, 2026, 1:41 p.m.
NER Named-entity recognition batch_69f6640168948190811bd5f933a87cf5 completed May 2, 2026, 8:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a1107a52c888190912e1e8f3175660d completed May 23, 2026, 1:49 a.m.
NEDg Description generation batch_6a11090be01081909db2a95c6d3afda7 completed May 23, 2026, 1:55 a.m.
NED2 Entity disambiguation (via description) batch_6a11098d46308190a3df9e8a74041538 completed May 23, 2026, 1:57 a.m.
PD Predicate disambiguation batch_69f6633451948190bcc0410602bb4914 completed May 2, 2026, 8:48 p.m.
Created at: April 22, 2026, 9:01 a.m.