refactor(celery Wave 5 P1 chunk 2): relocate ENTITY_RELATION_EXTRACTION import to aperag/indexing/llm

Wave 5 task #26 chunk 2 per §K.9.1 acceptance item 3 cascade
(legacy graphindex caller migration):

`aperag/service/prompt_template_service.py:155-163` (the
`get_default_prompt(prompt_type="graph")` branch) was importing the
ENTITY_RELATION_EXTRACTION template from the legacy
`aperag.domains.knowledge_graph.graphindex.prompts` module. Per chunk 1
relocate (`11113acb`), the canonical home for the template is now
`aperag.indexing.llm`. This commit migrates the import site so the
caller no longer transitively touches the legacy module.

Behavior unchanged — the legacy `graphindex/prompts.py` shim already
re-exports the template from the new location, so this is a pure
import-path refactor that leaves the runtime payload identical.

Local gates:
  - `ruff check ./aperag ./tests` clean
  - `ruff format --check ./aperag ./tests` clean (509 files)

Phase 1 cascade progress:
- chunk 1 ✅ (`11113acb`): §K.9 spec + `aperag/indexing/llm.py` relocate
- **chunk 2** (this commit): `service/prompt_template_service.py` import relocate
- chunk 3+ pending: `retrieval/pipeline.py` / `knowledge_graph/service.py` /
  `graph_curation/*` migration (these need new design — legacy
  24-method `GraphStore` Protocol → new 10-method `LineageGraphStore`
  Protocol API surface is NOT a 1-to-1 replacement; per Bryce
  msg=30c7e994 scope reality check + architect msg=b052b1b4 cascade
  ratify lane lock)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Author: Bryce

aperag/service/prompt_template_service.py

@@ -153,12 +153,13 @@ def get_hardcoded_index_prompt(prompt_type: str) -> Optional[str]:
         Hardcoded prompt content, or None if not available
     """
     if prompt_type == "graph":
-        # Return the graphindex v2 extraction prompt template. Unlike
-        # LightRAG's parameterised ``entity_extraction``, this one
-        # expects ``{input_text}`` / ``{entity_types}`` / ``{language}``
-        # / ``{max_entities}`` / ``{max_relations}`` to be filled by the
-        # caller (see ``aperag.domains.knowledge_graph.graphindex.prompts.render_extraction_prompt``).
-        from aperag.domains.knowledge_graph.graphindex.prompts import ENTITY_RELATION_EXTRACTION
+        # Return the canonical entity/relation extraction prompt template.
+        # Wave 5 P1 chunk 1 relocate (per §K.9.1 item 3): the canonical
+        # home is now :mod:`aperag.indexing.llm`. The template expects
+        # ``{input_text}`` / ``{entity_types}`` / ``{language}`` /
+        # ``{max_entities}`` / ``{max_relations}`` to be filled by the
+        # caller (see :func:`aperag.indexing.llm.render_extraction_prompt`).
+        from aperag.indexing.llm import ENTITY_RELATION_EXTRACTION
 
         return ENTITY_RELATION_EXTRACTION
     elif prompt_type == "summary":