This study focuses on developing a Named Entity Recognition (NER) system tailored specifically for low-resource languages spoken in Nigeria, namely Bassa, Ebira, and Okun. It sheds light on the crucial role of NER in natural language processing, underscoring the challenges encountered in creating NER systems for languages with limited resources, such as annotated data and linguistic tools. Its objective is to bridge this gap by offering a comprehensive overview of NER systems designed for these three Nigerian languages. The discussion delves into various approaches, hurdles, and recent progressions within the field. It stresses the significance of accurately identifying words for diverse language-processing tasks and emphasizes the meticulous process of collecting data, particularly text documents, in Bassa, Ebira, and Okun. Additionally the study uses machine learning approaches such as deep neural network (spaCy) based on Convolutional Neural Network (CNN) and Conditional Random Fields (CRF) which play an important role in the proper identification of named entities. Highlights the potential of recent advancements in machine learning and natural language processing to improve NER systems for languages facing resource constraints. This advancement not only enhances the accuracy and precision of NER but also advocates for the inclusivity and accessibility of NLP technologies on a global scale. The outcome of this endeavor manifests itself in promising results, with an impressive accuracy of 0.98, an F1-Score of 0.98, and a precision of 0.97 across all three languages.