Retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate external knowledge at inference.Graphbased RAG extends this by organizing corpora into knowledge graphs, improving multi-hop reasoning and offering a global understanding of the corpus.However, triplet-based graphs generated by LLMs are often fragmented and poorly connected, which reduces coherence and hinders reasoning.Prior enrichment methods such as clustering, community detection, or approximate graph algorithms attempt to restore connectivity but incur high computational cost and risk semantic distortion.To address these issues, we propose TH-RAG, a hierarchical framework that organizes triplets into subtopics and topics, enhancing connectivity, integrating dispersed information, and supporting robust multi-hop reasoning.Experiments on abstractive and specific QA benchmarks show that TH-RAG outperforms strong baselines in accuracy and robustness while remaining efficient, providing a scalable foundation for graph-based RAG systems.To support further research, we release our code in our GitHub repository.