This paper describes a method and technology for processing natural language texts and extracting data from the text that correspond to the semantics of an ontological model. The proposed method is distinguished by the use of a Large Language Model algorithm for text analysis. The extracted data are stored in an intermediate format, after which individuals and properties that reflect the specified semantics are programmatically created in the ontology. The proposed technology is implemented using the example of an ontological model that describes the geographical configuration and administrative–territorial division of Kazakhstan. The proposed method and technology can be applied in any subject areas for which ontological models have been developed. The results of the study can significantly improve the efficiency of using knowledge bases based on semantic networks by converting texts in natural languages into semantically linked data.

Currently, there is a rapid development of information technologies, the amount of information on the Internet is growing very fast and it is becoming increasingly difficult to find the necessary information. A search using keywords does not give results adequate to the meaning of the information sought. Therefore, the creation of a technology for designing intelligent question answering systems in the Kazakh language based on the presentation, processing and extraction of knowledge is a very actual problem, since it is in such a system that the linguistic and semantic relationships between the texts of the request and the answer can be taken into account. This research paper focuses on the integration of the Resource Description Framework (RDF) model, a semantic web technology, and provides a detailed evaluation of data mining techniques in Kazakh. The paper examines many Kazakh language data collection methods such as online scraping, community collaboration and translation. It also explores the function of RDF models in organizing knowledge, connecting data points and adding semantic richness to datasets. The paper discusses linguistic features and challenges unique to the Kazakh language and emphasizes the need to address these challenges with domain-specific data. The need for thorough cleaning, annotation and data quality assurance is emphasized to guarantee the reliability and use of the collected datasets. Within global communications and technology, the study emphasizes the importance of languages other than English and examines how semantic web technologies can improve data representation and knowledge retrieval. The study lays the groundwork for future initiatives to address the shortage of datasets in languages with fewer resources and to create semantic web technologies for language diversity.