Question Answering: The error message is not very clear after changing the "context" column's Data type to "Boolean" or "Int".

**System Information (please complete the following information):**
Windows OS: Windows-11-Enterprise-22H2
ML.Net Model Builder 2022: 17.17.0.2360601 (Main Build)
Microsoft Visual Studio Enterprise: 2022(17.7.7)
.Net: 6.0,7.0

**Describe the bug**
- On which step of the process did you run into an issue:
The error message is not very clear after changing the "context" column's Data type to "Boolean" or "Int".

**TestMatrix**
[Smallsuad.tsv.txt](https://github.com/dotnet/machinelearning-modelbuilder/files/13611600/Smallsuad.tsv.txt)

**To Reproduce**
Steps to reproduce the behavior:
1. Select Create a new project from the Visual Studio start window.
2. Choose the C# Console App (.NET Core) project template.
3. Add model builder by right click on the project.
4. Select **"Question Answering"** scenario.
5. On Data page, choose the data source, column.
6. Changing the "context" column's Data type to "Boolean" or "Int".
7. On the Train page. click "Start training".
8. Check the error message.

**Expected behavior**
The error message should be like "**Schema mismatch for Context column 'context': expected String, got Boolean/Int**".

**Screenshot**

**Additional context**
The bug is also repro after changing the "**answer_start**" column's Data type to "Boolean".
The error message should be like "**Don't know how to convert answer_start into Int32**".

Reproduziere den Question Answering-Ablauf mit der angehängten Datei Smallsuad.tsv.txt und ändere die Spaltentypen von context und answer_start, bevor du mit dem Training beginnst. Vergleiche die resultierenden Fehler mit den im issue erwarteten Meldungen; abgeschlossen ist die Aufgabe, wenn die Meldungen die erwarteten und tatsächlichen Typen für beide Spalten angeben.

Vom Indexierungsmodell aus dem Issue-Text verfasst.