Artificial Intelligence (AI) techniques enable the development of intelligent systems to solve problems in various fields of society. Many of these systems are considered black boxes, as they solve problems effectively, but the underlying knowledge driving the problem-solving process remains opaque. In this context, explainable AI has been developed to facilitate understanding of the systems work, increasing confidence in them, facilitating their acceptance, and satisfying technical and legal requirements. This work proposes an approach for generating knowledge-based explanations, which seek to be more accessible to different stakeholders. To achieve this objective, several AI technologies are integrated, such as neural networks, decision rules, ontologies, and knowledge graph, and the large language models. The proposal is illustrated with its application in a case study in the field of health and human expert evaluation.