This paper investigates the impact of restructuring knowledge graphs (KGs) with well-founded conceptual models to improve machine learning (ML) predictions, particularly in drug repurposing applications. These conceptual models were developed using OntoUML, which is grounded in the Unified Foundational Ontology, and were constructed following an established workflow for data FAIRification–a process aimed at making data more Findable, Accessible, Interoperable, and Reusable. We compared the performance of a Graph Neural Network model trained on original public KGs with models trained on the same restructured KGs. Our results indicate that while the ML model classification performance (measured in terms of accuracy and error metrics) remains similar for both, the models trained on restructured KGs produce more consistent predictions, reducing variability across multiple runs. These findings suggest that restructuring KGs using well-founded conceptual models can enhance the reliability of ML predictions without compromising model performance. We conclude by proposing future research directions to further explore the potential of conceptual models and FAIR principles in improving ML.