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: 2 tbsp vegetable oil 30 ml,1/4 cup chicken broth,2 carrots sliced thinly,1/2 cup frozen peas,4 scrambled eggs cooked,2 celery stalks chopped,2 garlic cloves finely chopped,1/2 tsp freshly ground black pepper 2 ml,4 cups cooked, cooled rice 1 L,3 cups cooked chicken, 750 ml cut into strips (about 3 breasts),1/4 cup chopped green onions,4 soy sauce 60 ml
- Assistant
{ "data": [ "30 ml chicken broth.", "2 carrots sliced thinly.", "120 ml frozen peas.", "4 scrambled eggs cooked.", "2 celery stalks chopped.", "2 garlic cloves finely chopped.", "1/2 tsp freshly ground black pepper.", "2 ml chicken broth.", "960 ml cooked, cooled rice.", "1000 ml cooked chicken.", "750 ml chicken cut into strips (about 3 breasts).", "60 ml chopped green onions.", "4 soy sauce.", "60 ml soy sauce." ] }
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.