Probabilistic topic models are powerful techniques which are widely used for discovering topics or semantic content from a large collection of documents. However, because topic models are entirely unsupervised, they may lead to topics that are not understandable in applications. Recently, several knowledge-based topic models have been proposed which primarily use word-level domain knowledge in the model to enhance the topic coherence and ignore the rich information carried by entities (e.g persons, location, organizations, etc.) associated with the documents. Additionally, there exists a vast amount of prior knowledge (background knowledge) represented as ontologies and Linked Open Data (LOD), which can be incorporated into the topic models to produce coherent topics. In this paper, we introduce a novel entity-based topic model, called EntLDA, to effectively integrate an ontology with an entity topic model to improve the topic modeling process. Furthermore, to increase the coherence of the identified topics, we introduce a novel ontology-based regularization framework, which is then integrated with the EntLDA model. Our experimental results demonstrate the effectiveness of the proposed model in improving the coherence of the topics.