Abstract: The new generation of artificial intelligence technologies, represented by large language models (LLMs), provides new opportunities for the structured representation and intelligent reasoning of geological knowledge. To address the challenges posed by the complexity of geoscientific knowledge systems, as well as the semantic fragmentation, limited reusability, and poor visualizability of unstructured texts, this study focuses on rare metal deposits in South China and proposes a unified strategy for constructing a knowledge graph that integrates deposit genesis and prospecting indicators. Based on the Deepseek R1-32B large language model and prompt engineering, the study automatically extracts and constructs a knowledge graph covering key rare metal elements such as Li, Be, Nb, Ta. Based on the knowledge graph construction and its extensibility analysis, the results indicate that rare metal mineralization in South China is closely associated with Indosinian and Yanshanian magmatic activities, characterized by significant high-degree fractionation and magmatic-hydrothermal processes. Rare metal elements exhibit a combinatorial anomaly of Li–Be–Nb–Ta–W–Sn. In summary, the knowledge graph constructed using LLMs reveals the multi-stage metallogenic mechanisms of rare metals in South China, clarifies the intrinsic relationships among geochemical anomalies, structural controls, and alteration zoning of rare metal deposits, and provides an intelligent research framework for the exploration of rare metals in South China and adjacent regions.