Merge pull request #235575 from dereklegenzoff/patch-6

fixing json formatting

Author: v-regandowner

articles/cognitive-services/openai/includes/prompt-chat-completion.md

@@ -34,9 +34,11 @@ Some other examples of system messages are:
 -	“You are an assistant designed to extract entities from text. Users will paste in a string of text and you will respond with entities you've extracted from the text as a JSON object. Here's an example of your output format:
 
 ```json
-{  "name": "",
+{  
+   "name": "",
    "company": "",
-   "phone_number": ""}”
+   "phone_number": ""
+}
 ```
 
 An important detail to understand is that even if you instruct a model in the system message to answer **I don't know** when unsure of an answer this does not guarantee that the request will be honored. A well designed system message can increase the likelihood of a certain outcome, but it is still possible that an incorrect response could be generated that contradicts the intent of the instruction in the system message.
@@ -164,4 +166,4 @@ Here is an example where the system is provided a [recent blog describing the la
 
 * [Learn more about Azure OpenAI](../overview.md).
 * Get started with the ChatGPT model with [the ChatGPT quickstart](../chatgpt-quickstart.md).
-* For more examples, check out the [Azure OpenAI Samples GitHub repository](https://github.com/Azure/openai-samples)
+* For more examples, check out the [Azure OpenAI Samples GitHub repository](https://github.com/Azure/openai-samples)