# What do these column headings mean?

{% hint style="info" %}
**Columns describe the rows** i.e. the rows represent the number of entries, and the values in the columns describe the attributes of these entries
{% endhint %}

When we look at a table of data, the first row (or rows) should indicate what the columns of data contain. For example, in the example below, it's fairly easy to guess that Gender, Population Group, Current Institution, Faculty, are all attributes of people. 

<figure><img src="https://lh3.googleusercontent.com/z8LdBy_ZNewv4gAA608GuRvcCf-wAmrpLkntKe4_Clh9ZucWY9p48J46fzOy5vcsPE26gnCnG1Dte1hNVXsYYUJOUu2_f8okMs6cEXW0vRJTe1ERkMXyxnXCCrIaTqSqZgC8HznvpEdvu7wcdcOk8Str81LBd5irr9V3t_lUJZ1QZQRGT8ts48_VQSs" alt=""><figcaption><p>Example </p></figcaption></figure>

But what about in this example, taken from an annual report published by the Department of Transport?&#x20;

<figure><img src="https://2315907434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fi8JLXAtCzbzpRcnAIJsv%2Fuploads%2FhidGnNbSj8f7rJkLFhAI%2Fimage.png?alt=media&#x26;token=2aeaa4cd-2902-4b03-b4cc-12dd1e0d8400" alt=""><figcaption></figcaption></figure>

You can probably figure out what the column **Geo\_type** is by reading down a few entries, and it seems obvious that **Pr\_code** relates to province. The rest of the table, however, is meaningless without something to interpret the variable names in the columns.&#x20;

Good data should come with "**metadata**" attached, either within the spreadsheet or or as a separate file. Metadata is data about the data, and can include an explaination of column headings, publication times, publisher names and methodoloogy used for collection. It should also tell you the licensing conditions for the dataset and whether or not you can use it.

Here's an example of metadata taken from a World Bank dataset.

<figure><img src="https://lh5.googleusercontent.com/ikhX6U-PdebHQULubl8yxIq4Oo2abDUNnw71UIuv4kn6CdcG9O_K2soteo4ZIVq0OXPXbx2agF3NEaVVJjbtddP36btY7GQdIUhaelLnpNLk9j15kk_ZHSK6AmZ4VkVKaEAnzXyGzKf0jiAeSSb9t4EB6g=s2048" alt=""><figcaption></figcaption></figure>

You can see this for yourself [at this link](https://data.worldbank.org/indicator/SP.DYN.LE00.IN?locations=ZG). Open it up and click on the button marked "Details". This will show you the first part of the metadata, along with more links to get more information.

Not all data comes with metadata attached. Be very wary about data you can't be 100% sure of though.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://openup.gitbook.io/training-content/the-fundamentals-of-data-driven-storytelling/module-3-verify/3.1-can-i-use-this-data-in-my-work/what-do-these-column-headings-mean.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.