Compare How Different Articles Report the Same News Event
Get a side-by-side table showing which facts all your pasted articles agree on, where they conflict, what each leaves out, and how each frames the story.
You getEvent in one sentence, table with columns and framing differences
Prompt
Act as a news analyst who checks how different outlets cover the same story.
I will paste two or more articles about the same event right after this message, each labeled with its outlet or a letter. Compare them so I can see what is solid and what is disputed.
Rules:
1. Use only what is in the pasted articles. Do not add outside facts or decide which source is right.
2. For every conflicting detail, quote or closely paraphrase each article's wording and name the source.
3. Mark a fact as Agreed only if every article states it. If only some mention it, mark it Missing in the others.
4. Flag every number (counts, dates, amounts, times) that differs between articles, even slightly.
5. Back each framing point with concrete evidence: headline wording, loaded words, who is quoted first, and what gets the most space.
Output format:
1. Event in one sentence.
2. Table with columns: Topic | one column per article | Status (Agreed / Conflicting / Missing).
3. Framing differences: 3-5 bullets with quoted evidence.
4. Solid vs. disputed: two short lists.
5. What to check next: 2-4 open questions, each with the type of primary source that would settle it.
End with one line on limits, such as later updates or several outlets relying on the same wire report.Example output
Tips and common edits
Why this works
- Requiring every article to state a fact before it counts as Agreed stops one-source claims from passing as settled.
- Demanding quoted evidence for framing turns vague bias talk into specific, checkable observations.
- Ending with primary sources to check gives a clear next step instead of a verdict the model can't support.
Use when a story is breaking or contested and outlets disagree. Paste the full text of each article, labeled by outlet. Works in ChatGPT, Claude or Gemini; long articles fit best in Claude.
Common edits
- Add a column for publication time to see how the story changed as it developed.
- Ask for a short neutral summary built only from the Agreed rows.
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Break Down a News Article into Facts, Opinions and Loaded Wording
Paste any news article and get a table of quoted claims labeled verifiable, interpretation or unattributed, plus loaded words, missing context and a pre-share checklist.
Check a Website's Reliability with Lateral Reading Before You Cite It
Get a five-point lateral reading check of any site or organization, with search steps to verify each point and a clear cite, cite-with-caution or avoid verdict.
Check Whether a Health Headline Matches the Study Behind It
Paste a headline and its study abstract to get a 1-5 accuracy score, a check table on study design and risk figures, and a plain-English rewrite.
Fact-Check a Viral Post or Forwarded Message Claim by Claim Before Sharing
Splits a viral post into separate claims, rates each one, and gives you exact search phrases and source types to confirm or debunk it before you share.
Spot Logical Fallacies and Weak Arguments in Any Opinion Piece
Returns a ranked table that quotes each weak passage in an essay, names the fallacy, explains in one line why it fails, and suggests evidence that would fix it.
Source Credibility Check with Claim-by-Claim Verification Plan
Lists every factual claim in a pasted article or claim, rates the evidence for each and says exactly what to verify and where.
- Check Whether a Statistic or Chart in an Article Is Used Honestly
- Build a Verification Checklist for AI Answers and Their Citations
- Trace a Quote or Claim Back to Its Original Source Step by Step
- Build a Literature Review Matrix from Pasted Abstracts with Gaps and Contradictions
- Code Interview Transcripts into Themes with Participant Counts and Verbatim Quotes
- Design a Bias-Checked Survey Where Every Question Informs a Decision