Automatic ontology generation is a necessary mandate for the age of Web 3.0 as the web is overloaded with information and with this extensive overload, its organisation demands to be taken seriously. This paper proposes an automatic strategy for ontology modelling and generation for ‘Diversity, Equity, and Inclusion Studies’ as the core domain where the entities from the dataset are outgrown successively using NELL and DBPedia knowledge stores and also a dynamic knowledge stack is generated from the World Wide Web which is, in turn, is handled and classified using the gated recurring units. The dataset itself is classified using Gated Recurrence Units (GRU). The explicit semantic analysis, normalized compression distance, and social engineering optimization provide stronger reasoning using semantic similarity and optimization models to increase the overall average precision, recall, accuracy, and F-measure and decrease the overall FDR of the model. This proposed model must be applied to the ultimate structure of the World Wide Web in at least one specific layer and must be achieved progressively and quickly. Ontologies are crisp knowledge representation and reasoning models and need to be conceived specifically for the very important domain of diversity, equity, and inclusion (DEI) studies.