[Bug]: Embedding pipeline bad column name

Do you need to file an issue?

[x] I have searched the existing issues and this bug is not already filed.
[x] My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
[x] I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.

Describe the bug

There is a title variable that gets use to access the entity titles within a dataframe before embedding the descriptions for that entity. Later in the code, this variable get updated with a description causing a KeyValue error.

Here are the two lines in question: https://github.com/microsoft/graphrag/blob/634e3ed62a6c5de7084f20e034edbb7185ad5e84/graphrag/index/operations/embed_text/embed_text.py#L180

https://github.com/microsoft/graphrag/blob/634e3ed62a6c5de7084f20e034edbb7185ad5e84/graphrag/index/operations/embed_text/embed_text.py#L196

Steps to reproduce

Build a brand-new index

Expected Behavior

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots