I have a list of ingredients that I would like to format in a simple and consistent way,…
- User
I have a list of ingredients that I would like to format in a simple and consistent way, following this structure:
"Quantity Unit Description."
Formatting Rules:
Quantity must be a number (e.g., "200" instead of "two hundred").
Unit must use the metric system and the corresponding abbreviated form (e.g., grams → g, liters → l, milliliters → ml, etc.).
Description should be the ingredient, including any specific details if mentioned (e.g., "brown sugar", "melted unsalted butter").
If an ingredient is already formatted correctly, do not change it.
Do not invent a quantity or unit if none is provided — leave it as is and just include the description.
If a line includes alternatives or multiple options (e.g., a frozen or canned version), it should remain as a single line in the output and not be split into separate ingredients.
Return Format: The result should be returned as a properly formatted JSON object, like this: json { "data": } Please reformat each ingredient in the list I will provide according to these guidelines.
Context Dump Ingredients source provided: ½ cup of flour (all-purpose),2 cups of water,1/4 cup of thinly sliced pimento-stuffed olives,4 tbsp vegetable oil,3 tbsp tomato paste,3 tbsp rum (dark),2 tsp salt,2 tsp tabasco,2 tsp sugar,2 lbs. cut into 1" pieces beef chucks (Boneless),2 cloves of minced garlic,2 large chopped onions,2 chopped bell peppers,14 oz chopped whole tomatoes with juice,1 Turkish bay leaf,Steamed white rice (optional)
- Assistant
{ "data": [ "125 ml flour (all-purpose).", "500 ml water.", "60 ml thinly sliced pimento-stuffed olives.", "60 ml vegetable oil.", "45 ml tomato paste.", "45 ml rum (dark).", "10 ml salt.", "10 ml tabasco.", "10 ml sugar.", "900 g cut into 1\" pieces beef chucks (Boneless).", "2 cloves minced garlic.", "2 large chopped onions.", "2 chopped bell peppers.", "400 g chopped whole tomatoes with juice.", "1 Turkish bay leaf.", "Steamed white rice (optional)." ] }
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.