# Who's On First data licenses — as retrieved

- Source: `https://whosonfirst.org/docs/licenses/`, and the dataset repository's own
  `https://raw.githubusercontent.com/whosonfirst/whosonfirst-data/master/LICENSE.md`
- Retrieved: 2026-09-21
- Publisher: Who's On First, originally Mapzen
- Version stated in the text: none. The page states it was generated by `bin/docs.py` on 2020-02-21.

Two pages carry the terms. They differ in length but agree in substance. The repository's
`LICENSE.md` is four paragraphs and links to the page. The page repeats those paragraphs and adds the
list of contributing sources.

## What the repository's `LICENSE.md` states, quoted in full

> Crediting Who's On First is recommended and linking back to the License is required. For example:
>
> > Data from Who's On First. [License](https://whosonfirst.org/docs/licenses/).
>
> The Who's On First dataset is both an original work and a modification of existing open data. Some
> of those open data projects do require attribution. We have listed all sources in the full
> [license file](https://whosonfirst.org/docs/licenses/).
>
> Remember, some sources require attribution, some do not. The format and structure that allows Who's
> On First to operate is made available under a
> [Creative Commons Zero](https://creativecommons.org/choose/zero/) designation, and
> [a shout out](https://twitter.com/mapzen/) would be lovely.

The wording separates three terms that are easy to confuse.

The project **recommends** crediting Who's On First and **requires** a link to the license. The
Creative Commons Zero designation covers the **format and structure**, in those words, and does not
cover the records.

## The contributing sources, measured

The page lists **102** sources, each with a link to its data and a link to its license. The count was
taken on 2026-09-21 by counting the `<name>: source data and license` entries on the retrieved page.

The page states that its list was generated on 2020-02-21. The dataset has changed since then, so the
list shows what contributed up to that date and does not show what a current bundle contains.

Four entries bear on questions this repository has open:

| entry                               | the license the page links      |
| ----------------------------------- | ------------------------------- |
| Ordnance Survey of Northern Ireland | `Open Government Licence v3.0`  |
| Ordnance Survey Ireland             | the publisher's own portal page |
| Yahoo! GeoPlanet                    | the publisher's own page        |
| GeoNames                            | the publisher's own page        |

**Royal Mail does not appear anywhere on the page.** The `candidate` bundle's record carried an open
question about "the Ordnance Survey and Royal Mail notice". The page does list the two Ordnance
Survey bodies, but it does not mention Royal Mail.

A separate census already addressed the GeoPlanet entry. Across the four Who's On First
bundles in the local data root, **zero of 7,189,494 `name:*` variant keys carry the `_p` GeoPlanet
suffix**, and neither postalcode bundle carries a `name:*` key at all, so no GeoPlanet-derived string
reaches a corpus row through those bundles.

## What this text does not settle

The text does not say which of the 102 sources contributed to a given record. The page lists the
sources for the dataset as a whole, and the per-record `src:geom` property records a geometry source
and not a name source. This file elects none of these terms, and every license decision in `address-source-register.json`
still reads `unchecked`.