Counts show all available guides. Filters combine to narrow your results.
Simplify a complex taskGuide
Decide what different kinds of sources can establish
Classify supplied made-up source descriptions relative to a research question and identify evidence limits.
Illustrative resourceNot tool-testedAdults who want a practical, low-stakes way to decide what different kinds of sources can establish
What you’re working towards
Classify supplied made-up source descriptions relative to a research question and identify evidence limits. The worked result is a written example for practice; the AI steps have not been tested.
Your choice also saves this guide’s current worked-example checkmarks. Only this browser; no account or sync. View saved guides
Saving needs JavaScript. Reading and downloading this guide does not save it.
Make a start
One step at a time.
3 steps
Start with the synthetic worked example or other non-sensitive inputs. Run one prompt at a time in your chosen AI tool. Replace any bracketed placeholders with the requested material, check each reply, and supply the source or earlier outputs that step needs. Paste them again if the tool lacks that context.
Start with the synthetic example, then adapt each prompt to your task.
01
Open a chat and paste the example
Open https://chatgpt.com and choose New chat. Copy every line under Input in this guide into the message box. Then add the prompt below (the instructions telling the assistant what to do) and send both together. Expect a written response shaped like the example under Output. The wording may differ. If the assistant asks for information already in the input, point to that line; if a necessary fact is missing, keep it unknown rather than guessing.
Your starting prompt
Classify the four supplied fictional source descriptions relative to the exact research question. Explain which is the most direct fit and why. Separate source type from reliability, keep the undated post’s provenance unresolved, and do not invent source contents or claim independent corroboration.
02
Check the specific result
A must be the strongest direct evidence for the gallery’s own wording. B can be primary without answering that exact question. C is later interpretation, and D must not count as an independent corroborating source. Compare it with the Input yourself. If the response fails a check, paste the correction prompt below into the same chat. Recheck the corrected version before saving it.
Your starting prompt
Recheck the classifications against author, date and the precise research question. Correct any claim that primary automatically means reliable or that D independently verifies A. Keep source contents limited to the descriptions provided.
03
Try it with your own example
Open a new chat. Copy the prompt below, then replace [PASTE YOUR INPUT HERE] with your own non-sensitive facts and rules. Include the kinds of details listed under Requirements. Send the whole message. Expect the same kind of result as this guide, using your values. Compare every name, number and rule with your input. If something differs, point to the exact mismatch and ask for a corrected complete answer. Save only a version you have checked.
Your starting prompt
Classify my source descriptions relative to the exact research question below. Identify the most direct fit with a reason. Separate source type from reliability, preserve unknown dates or provenance, and do not invent source contents or claim independent corroboration.
Use only the new input below. If a fact needed to finish is missing, ask me for it before choosing an answer.
MY INPUT
[PASTE YOUR INPUT HERE]
Optional: improve the result
Change the research question
See how the best source changes when the thing you want to establish changes. This extension uses the worked example. Return to that example chat, or paste its input and your checked example answer into a new chat first. Do not apply its sample values unchanged to your own input.
Advanced prompt
Keep all four source descriptions, but change the question to “How did one visitor describe the opening-day atmosphere?” Choose the most direct source and explain what its single-person perspective can and cannot establish.
Show, then try
See the shape of the result.
This input is synthetic. The output is a written illustration of the intended result, not a verified AI-tool run.
01 / The starting point
Synthetic input
Made-up example for practice.
Made-up research exercise. Question: how did the fictional North Hall gallery describe its own opening in 1925? Source A: a gallery-issued invitation printed in 1925 announcing the opening and calling it “a room for local makers.” Source B: a visitor’s diary entry written on opening day saying the room felt crowded. Source C: a historian’s article from 2005 discussing A and B. Source D: an undated online post repeating the phrase from A without naming a source. For this task, a primary source is direct material from the event or period being studied; a secondary source later interprets such material. Classification does not guarantee accuracy. Provenance means where a source came from and who created it. Do not claim the fictional gallery existed.
Copies text only. For image or file tasks, use the source files named in the steps too.
Written example for practice; not a recorded AI response.
A — Primary source and the most direct fit for this question: it is the gallery’s own opening invitation from 1925. It supports saying the gallery described the opening as “a room for local makers.”
B — Primary source for a visitor’s experience, but it does not directly establish the gallery’s own wording.
C — Secondary source: a later historian interprets A and B. It may help with context, but its claims would still need examination.
D — Provenance unresolved: author, date and source basis are not supplied. Do not use it as independent confirmation of A.
Best starting point: A, because the question asks about the gallery’s self-description. Being primary does not make every statement in a source accurate, and being secondary does not make it useless.
These checks use the worked example and its particular facts. With your own material, check your actual names, numbers, sources and rules; do not reuse the sample’s values as the answer.
Unsaved checks stay in this tab and reset when you reload. If you choose Save guide, its current example checkmarks are kept in this browser when storage is available.
!
A few things to watch for.
Source type depends on what you are studying. A later article could itself be primary evidence for a question about that later period.
Multiple pages repeating one uncredited statement are not necessarily multiple independent sources.