diff --git a/docs/tech-specs/agent-explainability.md b/docs/tech-specs/agent-explainability.md
index cb3a1816..f02a95b1 100644
--- a/docs/tech-specs/agent-explainability.md
+++ b/docs/tech-specs/agent-explainability.md
@@ -15,29 +15,41 @@ Add provenance recording to the React agent loop so agent sessions can be traced
 Both GraphRAG and Agent use PROV-O as the base ontology with TrustGraph-specific subtypes:
 
 ### GraphRAG Types
-| Entity | PROV-O Type | TG Type | Description |
-|--------|-------------|---------|-------------|
-| Question | `prov:Activity` | `tg:Question` | The user's query |
+| Entity | PROV-O Type | TG Types | Description |
+|--------|-------------|----------|-------------|
+| Question | `prov:Activity` | `tg:Question`, `tg:GraphRagQuestion` | The user's query |
 | Exploration | `prov:Entity` | `tg:Exploration` | Edges retrieved from knowledge graph |
 | Focus | `prov:Entity` | `tg:Focus` | Selected edges with reasoning |
 | Synthesis | `prov:Entity` | `tg:Synthesis` | Final answer |
 
 ### Agent Types
-| Entity | PROV-O Type | TG Type | Description |
-|--------|-------------|---------|-------------|
-| Question | `prov:Activity` | `tg:Question` | The user's query (same as GraphRAG) |
+| Entity | PROV-O Type | TG Types | Description |
+|--------|-------------|----------|-------------|
+| Question | `prov:Activity` | `tg:Question`, `tg:AgentQuestion` | The user's query |
 | Analysis | `prov:Entity` | `tg:Analysis` | Each think/act/observe cycle |
 | Conclusion | `prov:Entity` | `tg:Conclusion` | Final answer |
 
 ### Document RAG Types
-| Entity | PROV-O Type | TG Type | Description |
-|--------|-------------|---------|-------------|
-| Question | `prov:Activity` | `tg:Question` | The user's query (same as GraphRAG) |
+| Entity | PROV-O Type | TG Types | Description |
+|--------|-------------|----------|-------------|
+| Question | `prov:Activity` | `tg:Question`, `tg:DocRagQuestion` | The user's query |
 | Exploration | `prov:Entity` | `tg:Exploration` | Chunks retrieved from document store |
 | Synthesis | `prov:Entity` | `tg:Synthesis` | Final answer |
 
 **Note:** Document RAG uses a subset of GraphRAG's types (no Focus step since there's no edge selection/reasoning phase).
 
+### Question Subtypes
+
+All Question entities share `tg:Question` as a base type but have a specific subtype to identify the retrieval mechanism:
+
+| Subtype | URI Pattern | Mechanism |
+|---------|-------------|-----------|
+| `tg:GraphRagQuestion` | `urn:trustgraph:question:{uuid}` | Knowledge graph RAG |
+| `tg:DocRagQuestion` | `urn:trustgraph:docrag:{uuid}` | Document/chunk RAG |
+| `tg:AgentQuestion` | `urn:trustgraph:agent:{uuid}` | ReAct agent |
+
+This allows querying all questions via `tg:Question` while filtering by specific mechanism via the subtype.
+
 ## Provenance Model
 
 ```
diff --git a/trustgraph-base/trustgraph/provenance/__init__.py b/trustgraph-base/trustgraph/provenance/__init__.py
index 5a2f04b0..c1cb522a 100644
--- a/trustgraph-base/trustgraph/provenance/__init__.py
+++ b/trustgraph-base/trustgraph/provenance/__init__.py
@@ -78,6 +78,8 @@ from . namespaces import (
     # Explainability entity types
     TG_QUESTION, TG_EXPLORATION, TG_FOCUS, TG_SYNTHESIS,
     TG_ANALYSIS, TG_CONCLUSION,
+    # Question subtypes (to distinguish retrieval mechanism)
+    TG_GRAPH_RAG_QUESTION, TG_DOC_RAG_QUESTION, TG_AGENT_QUESTION,
     # Agent provenance predicates
     TG_THOUGHT, TG_ACTION, TG_ARGUMENTS, TG_OBSERVATION, TG_ANSWER,
     # Named graphs
@@ -159,6 +161,8 @@ __all__ = [
     # Explainability entity types
     "TG_QUESTION", "TG_EXPLORATION", "TG_FOCUS", "TG_SYNTHESIS",
     "TG_ANALYSIS", "TG_CONCLUSION",
+    # Question subtypes
+    "TG_GRAPH_RAG_QUESTION", "TG_DOC_RAG_QUESTION", "TG_AGENT_QUESTION",
     # Agent provenance predicates
     "TG_THOUGHT", "TG_ACTION", "TG_ARGUMENTS", "TG_OBSERVATION", "TG_ANSWER",
     # Named graphs
diff --git a/trustgraph-base/trustgraph/provenance/agent.py b/trustgraph-base/trustgraph/provenance/agent.py
index a62059c8..1f108795 100644
--- a/trustgraph-base/trustgraph/provenance/agent.py
+++ b/trustgraph-base/trustgraph/provenance/agent.py
@@ -18,6 +18,7 @@ from . namespaces import (
     PROV_ACTIVITY, PROV_ENTITY, PROV_WAS_DERIVED_FROM, PROV_STARTED_AT_TIME,
     TG_QUERY, TG_THOUGHT, TG_ACTION, TG_ARGUMENTS, TG_OBSERVATION, TG_ANSWER,
     TG_QUESTION, TG_ANALYSIS, TG_CONCLUSION,
+    TG_AGENT_QUESTION,
 )
 
 
@@ -62,6 +63,7 @@ def agent_session_triples(
     return [
         _triple(session_uri, RDF_TYPE, _iri(PROV_ACTIVITY)),
         _triple(session_uri, RDF_TYPE, _iri(TG_QUESTION)),
+        _triple(session_uri, RDF_TYPE, _iri(TG_AGENT_QUESTION)),
         _triple(session_uri, RDFS_LABEL, _literal("Agent Question")),
         _triple(session_uri, PROV_STARTED_AT_TIME, _literal(timestamp)),
         _triple(session_uri, TG_QUERY, _literal(query)),
diff --git a/trustgraph-base/trustgraph/provenance/namespaces.py b/trustgraph-base/trustgraph/provenance/namespaces.py
index 1375de94..15f1b7d3 100644
--- a/trustgraph-base/trustgraph/provenance/namespaces.py
+++ b/trustgraph-base/trustgraph/provenance/namespaces.py
@@ -72,7 +72,7 @@ TG_DOCUMENT = TG + "document"  # Reference to document in librarian
 TG_CHUNK_COUNT = TG + "chunkCount"
 TG_SELECTED_CHUNK = TG + "selectedChunk"
 
-# Explainability entity types (used by both GraphRAG and Agent)
+# Explainability entity types (shared)
 TG_QUESTION = TG + "Question"
 TG_EXPLORATION = TG + "Exploration"
 TG_FOCUS = TG + "Focus"
@@ -80,6 +80,11 @@ TG_SYNTHESIS = TG + "Synthesis"
 TG_ANALYSIS = TG + "Analysis"
 TG_CONCLUSION = TG + "Conclusion"
 
+# Question subtypes (to distinguish retrieval mechanism)
+TG_GRAPH_RAG_QUESTION = TG + "GraphRagQuestion"
+TG_DOC_RAG_QUESTION = TG + "DocRagQuestion"
+TG_AGENT_QUESTION = TG + "AgentQuestion"
+
 # Agent provenance predicates
 TG_THOUGHT = TG + "thought"
 TG_ACTION = TG + "action"
diff --git a/trustgraph-base/trustgraph/provenance/triples.py b/trustgraph-base/trustgraph/provenance/triples.py
index 8c21614e..14581c6f 100644
--- a/trustgraph-base/trustgraph/provenance/triples.py
+++ b/trustgraph-base/trustgraph/provenance/triples.py
@@ -24,6 +24,8 @@ from . namespaces import (
     TG_CHUNK_COUNT, TG_SELECTED_CHUNK,
     # Explainability entity types
     TG_QUESTION, TG_EXPLORATION, TG_FOCUS, TG_SYNTHESIS,
+    # Question subtypes
+    TG_GRAPH_RAG_QUESTION, TG_DOC_RAG_QUESTION,
 )
 
 from . uris import activity_uri, agent_uri, edge_selection_uri
@@ -315,6 +317,7 @@ def question_triples(
     return [
         _triple(question_uri, RDF_TYPE, _iri(PROV_ACTIVITY)),
         _triple(question_uri, RDF_TYPE, _iri(TG_QUESTION)),
+        _triple(question_uri, RDF_TYPE, _iri(TG_GRAPH_RAG_QUESTION)),
         _triple(question_uri, RDFS_LABEL, _literal("GraphRAG Question")),
         _triple(question_uri, PROV_STARTED_AT_TIME, _literal(timestamp)),
         _triple(question_uri, TG_QUERY, _literal(query)),
@@ -498,6 +501,7 @@ def docrag_question_triples(
     return [
         _triple(question_uri, RDF_TYPE, _iri(PROV_ACTIVITY)),
         _triple(question_uri, RDF_TYPE, _iri(TG_QUESTION)),
+        _triple(question_uri, RDF_TYPE, _iri(TG_DOC_RAG_QUESTION)),
         _triple(question_uri, RDFS_LABEL, _literal("DocumentRAG Question")),
         _triple(question_uri, PROV_STARTED_AT_TIME, _literal(timestamp)),
         _triple(question_uri, TG_QUERY, _literal(query)),