Not sure if you found this as well, but gpt-3.5-turbo-016 does a poor job following instructions other than parsing. So, to work around this, we prompt gpt-3.5-turbo with the rules we want applied say an extracted field and then go back to gpt-3.5-turbo-016 to parse with chatgpt functions.
Bottom line, every single post requires approximately 10 different prompts to refine the extraction.
Bottom line, every single post requires approximately 10 different prompts to refine the extraction.