<p>Inclusion of auxiliary information within a recommendation approach in form of a knowledge graph (KG) becomes a well-accepted technique for offering more accurate recommendation. It certainly addresses the data sparsity problem through exploring latent relationships and also increases the acceptance of the given solution by providing proper justifications behind the recommendations. Still, there is scope of improvement as the most of the existing works tried to explore all possible relations within the large search-space of the KG, which in turn increases the time requirements of the solution. Moreover, most of the works are not considering the context of the customer as a focal issue. In this work, we have proposed a context sensitive collaborative recommendation approach using KG. This approach considers the context information of a customer as focal issues, thereby reducing the propagation within the KG compared to existing attempts. The solution delivers more relevant recommendation to the customers considering context information and also ensures the delivery of the solution within lesser time. This makes the proposed solution effective, even for time-constrained application. The proposed concept is implemented through rigorous experimentation on benchmark datasets for necessary validation. We have also compared the proposed approach with the existing state of the art approaches and significant improvement is noted in terms of both accuracy and time.</p>