The law has language at its core, so it is not surprising that software operating on natural language has played a role in certain areas of the legal industry for a long time. The last few years have seen a significant upsurge of interest in this area, including an increasing number of start-ups applying deep learning techniques in the context of specific legal applications. In this paper, we present a simple yet powerful method that is applied to legal documents from different legal bodies to correctly recognize a numerous entity to find relevant information for some specific matter at hand. To the best of our knowledge, no attempt has been made in this direction so far and as such our work opens a new direction of research, which will be very much useful for the society. © Springer Nature Singapore Pte Ltd 2021.