Triple

T14416434
Position Surface form Disambiguated ID Type / Status
Subject Charlevoix Municipal Airport E357464 entity
Predicate IATAcode P418 FINISHED
Object CVX
CVX is the three-letter IATA airport code for Charlevoix Municipal Airport in Charlevoix, Michigan, United States.
 E1096689 NE FINISHED

How this triple was built (4 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: CVX | Statement: [Charlevoix Municipal Airport, IATAcode, CVX]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CVX
Context triple: [Charlevoix Municipal Airport, IATAcode, CVX]
  • A. CVX
    CVX is the stock ticker symbol for Chevron Corporation, a major American multinational energy and oil company.
  • B. Convex Optimization
    Convex Optimization is a widely used graduate-level textbook that systematically develops the theory, algorithms, and applications of convex optimization problems in engineering, statistics, and applied mathematics.
  • C. SCIP
    SCIP is the ICAO airport code for Mataveri International Airport, the main air gateway to Easter Island in Chile.
  • D. Karush–Kuhn–Tucker conditions
    The Karush–Kuhn–Tucker conditions are fundamental optimality criteria in nonlinear programming that generalize Lagrange multipliers to handle inequality constraints.
  • E. CVK
    CVK is a major campus of Charité – Universitätsmedizin Berlin, housing extensive clinical and research facilities in the Wedding district of Berlin.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: CVX
Triple: [Charlevoix Municipal Airport, IATAcode, CVX]
Generated description
CVX is the three-letter IATA airport code for Charlevoix Municipal Airport in Charlevoix, Michigan, United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CVX
Target entity description: CVX is the three-letter IATA airport code for Charlevoix Municipal Airport in Charlevoix, Michigan, United States.
  • A. CVX
    CVX is the stock ticker symbol for Chevron Corporation, a major American multinational energy and oil company.
  • B. Convex Optimization
    Convex Optimization is a widely used graduate-level textbook that systematically develops the theory, algorithms, and applications of convex optimization problems in engineering, statistics, and applied mathematics.
  • C. SCIP
    SCIP is the ICAO airport code for Mataveri International Airport, the main air gateway to Easter Island in Chile.
  • D. Karush–Kuhn–Tucker conditions
    The Karush–Kuhn–Tucker conditions are fundamental optimality criteria in nonlinear programming that generalize Lagrange multipliers to handle inequality constraints.
  • E. CVK
    CVK is a major campus of Charité – Universitätsmedizin Berlin, housing extensive clinical and research facilities in the Wedding district of Berlin.
  • F. None of above. chosen

Provenance (5 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_69d82793421c8190861eb0e673b085de completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de90cc99208190a2313b1acfb5d802 completed April 14, 2026, 7:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd552bc32c81908a562732e3950442 completed May 8, 2026, 3:14 a.m.
NEDg Description generation batch_69fd55d90ed08190b6a0184715f39ff4 completed May 8, 2026, 3:17 a.m.
NED2 Entity disambiguation (via description) batch_69fd565d32fc8190acc1e733537a23cb completed May 8, 2026, 3:19 a.m.
Created at: April 10, 2026, 1:17 a.m.