Khasa Gillani, Erik Novak, Klemen Kenda and Dunja Mladenić

ABSTRACT
The advent of Large Language Models (LLMs), such as Chat-
GPT and GPT-4, has revolutionized natural language process-
ing, opening avenues for advanced textual understanding. This
study explores the application of LLMs in developing Knowledge
graphs from textual data. Knowledge graphs offer a structured
representation of information, facilitating enhanced comprehen-
sion and utilization of unstructured text. We intend to construct
Knowledge graphs that capture relationships and entities within
diverse textual datasets by harnessing LLMs’ contextual under-
standing and language generation capabilities. The primary goal
is to explore and understand how well LLMs can identify and
extract relevant entities and relationships from textual data using
prompt engineering while contributing to structured knowledge
representation.