Status: True
Assertion
Diamonds come from coal.
Results
The given information confirms that some carbon-rich deposits may contain diamond-bearing kimberlite or lamproite rocks, which are capable of transporting diamonds during volcanic eruptions. Additionally, the geological conditions necessary for diamond formation can indeed be present in certain coal deposits with inclusions of these types of rocks. Therefore, based on this information, we classify the statement as true.
===
True: The provided details align accurately with established scientific understanding regarding the presence of carbon-rich deposits containing kimberlite or lamproite rock formations that can transport diamonds to the Earth’s surface during volcanic eruptions, and their role in providing suitable conditions for diamond formation within coal deposits.
Assumptions
<|assistant|> Assumptions supporting the statement “Diamonds come from coal”:
– Some carbon-rich deposits, such as lignite or brown coal, may contain diamond-bearing kimberlite or lamproite rocks.
– Kimberlite and lamproite pipes can transport diamonds to the Earth’s surface during volcanic eruptions.
– The geological conditions necessary for diamond formation, such as high pressure and temperature in the mantle, are present in certain coal deposits with kimberlite or lamproite inclusions.
– Kimberlite and lamproite rocks containing diamonds can be economically extracted from these coal deposits, making it feasible to mine for diamonds within them.
– The prevalence of diamond formation in specific types of coal deposits is significant enough that the mining industry considers such locations as potential sources for diamond extraction.
It’s worth noting that while this statement may hold some truth, it doesn’t fully capture the complexity and rarity of finding diamonds within certain coal formations. Most commercially viable diamond
Fact Checker Output
== Response ==
1. Some carbon-rich deposits may contain diamond-bearing kimberlite or lamproite rocks: True. Kimberlites and lamproites are known to transport diamonds from their mantle source to the Earth’s surface during volcanic eruptions. These rocks can indeed be found within carbon-rich deposits, although such occurrences are relatively rare compared to other sources of diamonds like kimberlite pipes in stable continental regions.
2. Kimberlite and lamproite pipes transport diamonds during volcanic eruptions: True. These types of volcanic rocks have the unique ability to transport diamonds from deep within the Earth’s mantle (typically over 140 kilometers below the surface) up to the crust, where they are then exposed at or near the Earth’s surface through volcanic eruptions.
3. The geological conditions necessary for diamond formation are present in certain coal deposits with kimberlite or lamproite inclusions: True. Kimberlite and lamproite rocks have formed under high-press
Model Used
microsoft/Phi-3-mini-4k-instruct-gguf
Script Name
fact_checker_mongodb.py
Script Code
import os
import sys
import requests
from langchain_openai.llms import OpenAI
from langchain.prompts import PromptTemplate
from dotenv import load_dotenv
from statements import get_random_statement
from mongodb_helper import insert_record # Import MongoDB helper functions
import html
# Load environment variables from .env file
load_dotenv()
# Define category IDs
CATEGORY_IDS = {
"True": 2,
"False": 3,
"Debatable": 4,
"Unknown": 6
}
def create_wordpress_post(title, content, category):
data = {
"title": title,
"content": content,
"status": "publish",
"categories": [CATEGORY_IDS[category]]
}
response = requests.post(
os.getenv("WORDPRESS_POSTS_URL"),
json=data,
auth=(os.getenv("WORDPRESS_USERNAME"), os.getenv("WORDPRESS_PASSWORD"))
)
if response.status_code == 201:
print("Blog post created successfully.")
else:
print(f"Failed to create blog post: {response.status_code} - {response.text}")
def fact_check(assertion):
llm = OpenAI(temperature=0.7, model=os.getenv("MODEL_NAME"))
# Define the prompt templates
assertion_template = """{assertion}\n\n"""
assertion_prompt = PromptTemplate(input_variables=["assertion"], template=assertion_template)
assumptions_template = """Here is a statement:
{statement}
Make a bullet point list of the assumptions required to support the above statement.\n\n"""
assumptions_prompt = PromptTemplate(input_variables=["statement"], template=assumptions_template)
fact_checker_template = """Here is a bullet point list of assertions:
{assertions}
For each assumption, determine whether it is true or false. Explain your reasoning.\n\n"""
fact_checker_prompt = PromptTemplate(input_variables=["assertions"], template=fact_checker_template)
answer_template = """
Here is the information to classify the statement:
{facts}
Based on the above information, how would you classify the statement? Respond with one of the following options followed by a colon and space:
- True: [Explanation]
- False: [Explanation]
- Debatable: [Explanation]
"""
answer_prompt = PromptTemplate(input_variables=["facts"], template=answer_template)
# Format prompts and extract the string content
formatted_assertion = assertion_prompt.format_prompt(assertion=assertion).text
assertion_output = llm.invoke(formatted_assertion)
formatted_assumptions = assumptions_prompt.format_prompt(statement=assertion_output).text
assumptions_output = llm.invoke(formatted_assumptions)
formatted_fact_checker = fact_checker_prompt.format_prompt(assertions=assumptions_output).text
fact_checker_output = llm.invoke(formatted_fact_checker)
formatted_answer = answer_prompt.format_prompt(facts=fact_checker_output).text
final_output = llm.invoke(formatted_answer)
return {
"assertion_output": assertion_output,
"assumptions_output": assumptions_output,
"fact_checker_output": fact_checker_output,
"final_output": final_output,
}
def extract_status_and_reasoning(final_output):
final_output = final_output.strip()
if "True:" in final_output:
status_start = final_output.find("True:")
status = "True"
elif "False:" in final_output:
status_start = final_output.find("False:")
status = "False"
elif "Debatable:" in final_output:
status_start = final_output.find("Debatable:")
status = "Debatable"
else:
return "Unknown", final_output
reasoning = final_output[status_start + len(status) + 1:].strip()
return status, reasoning
if __name__ == "__main__":
if len(sys.argv) > 1:
assertion = sys.argv[1]
else:
assertion = get_random_statement()
print(assertion)
submission = fact_check(assertion)
# Print the detailed outputs to inspect their structure
for key, value in submission.items():
print(f"{key}: {value}")
# Extract the final output for status determination and reasoning
final_output = submission['final_output']
status, reasoning = extract_status_and_reasoning(final_output)
# Record the result in MongoDB
try:
print("Attempting to insert record into MongoDB...")
insert_record(
script_name="fact_checker_mongodb.py",
script_code=html.escape(open(__file__).read()),
assertion=assertion,
status=status,
submission=submission, # Store the entire submission for detailed analysis
model=os.getenv("MODEL_NAME")
)
print("Record inserted into MongoDB successfully.")
except Exception as e:
print(f"Failed to insert record into MongoDB: {e}")
print(final_output)
# Create a blog post on WordPress
blog_title = f"Fact Check: {assertion}"
blog_content = f"""
<h1>Status: {status}</h1>
<h2>Assertion</h2>
<p>{assertion}</p>
<h2>Results</h2>
<p>{reasoning}</p>
<h3>Assumptions</h3>
<p>{submission['assumptions_output']}</p>
<h3>Fact Checker Output</h3>
<p>{submission['fact_checker_output']}</p>
<h4>Model Used</h4>
<p>{os.getenv("MODEL_NAME")}</p>
<h4>Script Name</h4>
<p>fact_checker_mongodb.py</p>
<h4>Script Code</h4>
<pre>{html.escape(open(__file__).read())}</pre>
"""
create_wordpress_post(blog_title, blog_content, status)
Leave a Reply