We examine a knowledge representation architecture to support context interchange mediation. For autonomous receivers and sources sharing a common subject domain, the mediator's reasoning engine can devise query plans integrating multiple sources and resolving semantic heterogeneity. Receiver applications obtain the data they need in the form they need it without imposing changes on sources. The KR architecture includes: 1) data models for each source and receiver, 2) subject domain ontologies, containing abstract subject matter conceptualizations that would be known to experienced practitioners in the industry, and 3) context models for each source and receiver that explain how each source or receiver data model implements the abstract concepts from a subject domain ontology. Examples drawn from the fixed income securities industry illustrate problems and solutions enabled by the proposed architecture Includes bibliographical references (leaf [6]) We examine a knowledge representation architecture to support context interchange mediation. For autonomous receivers and sources sharing a common subject domain, the mediator's reasoning engine can devise query plans integrating multiple sources and resolving semantic heterogeneity. Receiver applications obtain the data they need in the form they need it without imposing changes on sources. The KR architecture includes: 1) data models for each source and receiver, 2) subject domain ontologies, containing abstract subject matter conceptualizations that would be known to experienced practitioners in the industry, and 3) context models for each source and receiver that explain how each source or receiver data model implements the abstract concepts from a subject domain ontology. Examples drawn from the fixed income securities industry illustrate problems and solutions enabled by the proposed architecture