refactor(llm): improve graph extraction default prompt

[Kryst4lDem0ni4s]

fix #185

After modifying the prompt configuration file (incubator-hugegraph-ai\hugegraph-llm\src\hugegraph_llm\config\prompt_config.py), the output has significantly improved.

For the generic input and schema example, the output being generated now is:

{
  "vertices": [
    {
      "id": "1:Sarah",
      "label": "person",
      "type": "vertex",
      "properties": {
        "name": "Sarah",
        "age": 30,
        "occupation": "attorney"
      }
    },
    {
      "id": "1:James",
      "label": "person",
      "type": "vertex",
      "properties": {
        "name": "James",
        "occupation": "journalist"
      }
    },
    {
      "id": "2:SarahsPlace",
      "label": "webpage",
      "type": "vertex",
      "properties": {
        "name": "SarahsPlace",
        "url": "www.sarahsplace.com"
      }
    }
  ],
  "edges": [
    {
      "id": 1,
      "label": "roommate",
      "type": "edge",
      "outV": "1:Sarah",
      "outVLabel": "person",
      "inV": "1:James",
      "inVLabel": "person",
      "properties": {
        "date": "2010"
      }
    },
    {
      "id": 2,
      "label": "link",
      "type": "edge",
      "outV": "2:SarahsPlace",
      "outVLabel": "webpage",
      "inV": "1:Sarah",
      "inVLabel": "person",
      "properties": {}
    }
  ]
}

from the previous errenous output:

"vertices": [
   {
     "id": "1:person",
     "label": "person",
     "type": "vertex",
     "properties": {
       "name": "Sarah",
       "age": "30",
       "occupation": "attorney"
     }
   },
   {
     "id": "1:webpage",
     "label": "webpage",
     "type": "vertex",
     "properties": {
       "name": "www.sarahsplace.com",
       "url": "None"
     }
   }
 ],
 "edges": [
   {
     "label": "roommate",
     "type": "edge",
     "outV": "1:person",
     "outVLabel": "person",
     "inV": "1:webpage",
     "inVLabel": "webpage",
     "properties": {
       "date": "2010"
     }
   }
 ]
}

This significant improvement is possible by clearly outlining the data type and conditional requirements.
Tested locally and through API.

[imbajin]

THX, the context is clearly~ (we'll review/test it soon)

[imbajin]

THX