Retrieval-augmented generation (RAG) frequently integrates knowledge graphs (KGs) for complex multi-hop question answering. However, their performance is increasingly bottlenecked by the knowledge structuring and reasoning processes. (i) Severe semantic loss: Distilling continuous texts into discrete symbols strips away contextual nuances and narrative coherence. (ii) Pronounced modality mismatch: Fragmented graph structures clash with the continuous texts LLMs are pre-trained on, while rewriting them into natural language introduces generative noise and omits information. To address these limitations, we propose **ThreadRAG**, a semantic-topology-based RAG framework for context-preserving knowledge structuring and modality-native evidence reasoning. ThreadRAG introduces a **S**emantic **T**opology **M**apper (**STM**), which organizes retrieved documents into context-intact Semantic Nodes and constructs a **S**emantic **T**opology **G**raph (**STG**) through narrative, semantic, and lexical edges. It further incorporates **E**nergy-**D**riven **P**athfinding (**EDP**), which identifies query-relevant subgraphs via energy diffusion and deterministically linearizes them into coherent textual evidence paths. Experiments on three multi-hop QA benchmarks demonstrate that ThreadRAG consistently outperforms strong baselines. Notably, it achieves a 14.4% EM improvement over text-centric methods on HotpotQA and surpasses the best baseline by 5.8% EM on 2WikiMultihop, while reducing token cost to 23.3% of the strongest baseline.