diff --git a/src/pipelines/saas/prompts/prompt_calls.py b/src/pipelines/saas/prompts/prompt_calls.py
index f760ada..ae17891 100644
--- a/src/pipelines/saas/prompts/prompt_calls.py
+++ b/src/pipelines/saas/prompts/prompt_calls.py
@@ -5,9 +5,8 @@ import src.config as config
 import src.prompts.prompt_templates as prompt_templates
 from src.constants.constants import Constants
 from src.constants.investment_columns import FIELD_FORMAT_MAPPING
-from src.constants.delimiters import Delimiter
 from src.prompts.fieldset import Field, FieldSet
-from src.utils import llm_utils, string_utils
+from src.utils import llm_utils, string_utils, json_utils
 from src.pipelines.shared.preprocessing import preprocessing_funcs
 from src.utils.formatting_utils import normalize_field_value
 from src.pipelines.shared.extraction import tin_npi_funcs
@@ -650,10 +649,9 @@ def prompt_header_deduplication(
     )
 
     try:
-        llm_answer_final = string_utils.extract_text_from_delimiters(
-            llm_answer_raw, Delimiter.PIPE
-        )
-        deduped_dict = json.loads(llm_answer_final)
+        # parse_json_dict tolerates prose before/after the JSON body and
+        # pipe/brace wrappers, unlike strict pipe-delimiter extraction.
+        deduped_dict = json_utils.parse_json_dict(llm_answer_raw)
 
         if not isinstance(deduped_dict, dict) or not deduped_dict:
             logging.warning(
diff --git a/src/prompts/investment_prompts.json b/src/prompts/investment_prompts.json
index e15d08c..0e30ffe 100644
--- a/src/prompts/investment_prompts.json
+++ b/src/prompts/investment_prompts.json
@@ -676,7 +676,7 @@
         "field_name": "DISCOUNT_TERM",
         "relationship": "one_to_n",
         "field_type": "special_case_check",
-        "prompt": "Describes a discount applied to the payment. The description must include the term 'Discount' and should specify the discount amount, percentage, or type.",
+        "prompt": "Describes a contract-wide or methodology-wide discount applied to the standard reimbursement rate (not a per-service rate expressed using discount language). The reimbursement text MUST contain the literal word 'discount' (case-insensitive). Do NOT classify as DISCOUNT_TERM when the discount IS the base rate for a specific service in a rate table — for example, table rows like 'Contact Lenses: 2% discount', 'Frame: 20% discount', or 'Progressive Lenses: 15% discount' are per-service base rates (classify as PAYMENT_CARVEOUT or BASE_COVERED_SERVICES, NOT DISCOUNT_TERM). Only classify as DISCOUNT_TERM when the discount is a separate provision that reduces payment across all services or the fee schedule overall, e.g., 'a 10% discount applies to all Covered Services', 'payments will be discounted by 5% across the board', or 'provider agrees to a 3% prompt-pay discount'.",
         "breakout_template": "DISCOUNT_BREAKOUT"
     },
     {
@@ -707,7 +707,7 @@
         "field_name": "PREMIUM_TERM",
         "relationship": "one_to_n",
         "field_type": "special_case_check",
-        "prompt": "Describes a premium to the payment. Look for the term 'Premium'. Classify as a premium only if the text explicitly indicates an increase or addition to the standard payment rate, such as 'an additional premium of X%', 'a premium rate of Y% above standard', or 'premium payment terms apply'.",
+        "prompt": "Describes an explicit premium or surcharge on top of a base payment. The reimbursement text MUST contain the literal word 'premium' (case-insensitive) to qualify. Do NOT classify as PREMIUM_TERM merely because a rate is expressed as a percentage above 100% of a reference schedule — for example, '110% of CMS allowed', '105% of Medicare', '120% of the fee schedule', or similar are base reimbursement rates (BASE_COVERED_SERVICES), NOT premiums. Only classify as PREMIUM_TERM when the contract language explicitly uses premium/surcharge terminology, such as 'an additional premium of X%', 'a premium rate of Y% above standard', 'premium payment terms apply', or 'Z% premium added to the base rate'.",
         "breakout_template": "PREMIUM_BREAKOUT"
     },
     {
diff --git a/src/prompts/prompt_templates.py b/src/prompts/prompt_templates.py
index 6022c25..94faa01 100644
--- a/src/prompts/prompt_templates.py
+++ b/src/prompts/prompt_templates.py
@@ -2118,6 +2118,7 @@ Rules for Exclusion:
 * Do NOT include docusign IDs and other metadata
 * Do NOT include partial sentences or continuation text
 * Do NOT include form field labels like "Provider's Legal Name" or "Authorized Representative's Signature"
+* Do NOT include page-footer text. Footers appear near the bottom of a page adjacent to page numbers, contract/reference numbers, effective dates, or docusign IDs, and often repeat a SHORTENED form of the real exhibit identifier. For example, if the top-of-page header is "ATTACHMENT A-2 Oregon Health & Science University Effective 07/01/2025 Reimbursement Schedule", a bottom-of-page line like "Attachment A Oregon Health & Science University" next to "Page 2" or a contract number IS a footer, NOT a new section header — exclude it. When the same chunk contains a long-form exhibit header AND a short-form repeat of the same exhibit identifier near page metadata, keep only the long-form header.
 
 [OUTPUT FORMAT]
 Return a JSON dictionary enclosed in |pipes| where: