diff --git a/fieldExtraction/src/prompts/prompt_templates.py b/fieldExtraction/src/prompts/prompt_templates.py
index ba7fed7..3cf9bb3 100644
--- a/fieldExtraction/src/prompts/prompt_templates.py
+++ b/fieldExtraction/src/prompts/prompt_templates.py
@@ -535,6 +535,7 @@ Use the text in the Service to populate a JSON dictionary with the following fie
 - If the text describes an entire Code Category (not one specific code) based on a start letter, return the Category in the form "Category: X". e.g. "A-Codes" --> "Category: A", "K-Codes" --> "Category K", etc.
 - If the text explicitly says that there is no published or established rate, write "NOT_ESTABLISHED" for the PROCEDURE_CD value.
 - If any of the codes are not found, do not write a list for that field. Simply populate the field with an empty list [].
+- If a 3-digit code is found without any explicit code type indicators (e.g., no mention of “DRG”, “revenue”, “Rev code”, etc.), check the surrounding text for contextual clues to determine whether it refers to a Revenue Code or a Grouper Code. If no clear context is found, default to classifying it as a GROUPER_CD.
 
 Here is the Service to analyze:
 Service: {service.replace('"', "'")}