Clean README: no external references, passage_entity naming

README.md

@@ -36,7 +36,11 @@ pip install -r requirements.txt
 # 2. Set your OpenAI API key (required for LLM and answer generation)
 export OPENAI_API_KEY="sk-..."
 
-# 3. Download pre-built KGs (recommended — saves hours of build time + API costs)
+# 3. KGs are already included (no download needed when cloned from HuggingFace)
+#    If cloned from GitHub, download KGs:
+#    huggingface-cli download tarzanagh/QAFD-RAG --include "kg/multihop/*" --local-dir .
+
+# (Original step 3: Download pre-built KGs (recommended — saves hours of build time + API costs)
 huggingface-cli download tarzanagh/QAFD-RAG --include "kg/multihop/*" --local-dir .
 huggingface-cli download tarzanagh/QAFD-RAG --include "kg/ultradomain/*" --local-dir .
 
@@ -92,7 +96,7 @@ QAFD-RAG/
 │   ├── retrievers/
 │   │   ├── flow_diffusion.py        # QAFD on NetworkX (entity graph)
 │   │   └── base.py                  # Retriever interface
-│   ├── hipporag_pipeline/           # Passage-entity graph pipeline
+│   ├── passage_entity/           # Passage-entity graph pipeline
 │   │   ├── kg_builder.py            # OpenIE → igraph (entities + passages + facts)
 │   │   ├── graph_adapter.py         # QAFD on igraph (passage-entity graph)
 │   │   ├── retriever.py             # Fact reranking → seed selection → QAFD