pup: fix investor => invested

llm_prompts.py

@@ -82,8 +82,8 @@ This is the most critical part of your task. A bad choice leads to a useless, bo
     *   If the query compares concepts like "cancer vs. infection," the dimension is `therapeutic_category`.
     *   If the query compares "oral vs. injection," the dimension is `route_branch`.
     *   For general "recent news" or "top deals," `news_type` or `company_name` are often good starting points.
-    *   if the query is about "recent deals about infection" the dimension should be `company_name_investor`. if we choose company_name as dimension, we got duplicate data. because this field contains 
-    both investor and invested companies. So we need to use company_name_investor as dimension in this type of scenarios.
+    *   if the query is about "recent deals about infection" the dimension should be `company_name_invested`. if we choose company_name as dimension, we got duplicate data. because this field contains 
+    both investor and invested companies. So we need to use company_name_invested as dimension in this type of scenarios.
     *   Your goal is to find a dimension that reveals a meaningful pattern in the filtered data.
 
 **2. Choosing the `analysis_measure` (The metric):**