Democracy's Library place tags
x_dl_tagsrelease v0.7.1CC0 1.0
About
Extraction table: Democracy's Library (IGS) items about SF, with the neighbourhoods, streets and places each is about (claude-haiku-5-5 on metadata + first OCR, dl_tag.py).
- Where it comes from
- Documents about San Francisco in Democracy's Library on the Internet Archive.
- How it was read
- The neighbourhoods, streets and places each document is about, read by a language model (Claude Haiku) from its description and first pages.
- How far to trust it
- The release passed its automatic checks before it was published (what is checked). A hand check by the editor of qipu data is under way: 36 of 38 items checked so far were right, on votes, money, places and the map. A row says what the record states; the scanned page is the authority. Details
- Licence
- CC0 1.0: use it for anything, no permission needed. The scans and other sources keep their own rights.
- Version
- v0.7.1, published 21 October 2026. A published release is never changed; corrections come as a new release.
Technical details
- Table
- x_dl_tags
- Rows
- 1,131
- Columns
- 10
- Parquet
- x_dl_tags.parquet, < 0.1 MB
- Version
- v0.7.1, 21 October 2026
- Licence
- CC0 1.0. Sources keep their own rights.
Rows
Rows by doc_type
| Value | Rows | Share | |
|---|---|---|---|
| study or report | 578 | 51.1% | |
| plan | 205 | 18.1% | |
| other | 131 | 11.6% | |
| ordinance or legislation | 70 | 6.2% | |
| annual report | 53 | 4.7% | |
| environmental impact report | 46 | 4.1% | |
| audit | 19 | 1.7% | |
| minutes or proceedings | 15 | 1.3% | |
| city-owned property report | 14 | 1.2% |
Rows by scope
| Value | Rows | Share | |
|---|---|---|---|
| regional | 492 | 43.5% | |
| citywide | 380 | 33.6% | |
| site | 111 | 9.8% | |
| neighbourhoods | 85 | 7.5% | |
| not San Francisco | 63 | 5.6% |
Method and accuracy
The neighbourhoods, streets and places each document is about, read by a language model (Claude Haiku) from its description and first pages.
| Field | Made by | How well it is known |
|---|---|---|
| x_dl_tags (places a DL item is about) | LLM on metadata + first OCR | unmeasured (no gold of document places yet). |
The release passed its automatic checks before it was published (what is checked). A hand check by the editor of qipu data is under way: 36 of 38 items checked so far were right, on votes, money, places and the map. A row says what the record states; the scanned page is the authority.
Columns 10
| Column | Type | Can be empty | Privacy | Public copy | Description |
|---|---|---|---|---|---|
| about_sf | BOOLEAN | yes | none | as is | True when the document is about San Francisco, chosen by a model from the catalogue record and the start of the OCR. |
| doc_type | VARCHAR | yes | none | as is | Document type (study or report, plan, environmental impact report, budget, ...), chosen by a model from the catalogue record and the start of the OCR.Values annual report, audit, city-owned property report, environmental impact report, minutes or proceedings, ordinance or legislation, other, plan, study or report |
| scope | VARCHAR | yes | none | as is | citywide, neighbourhoods, site, regional or not San Francisco, chosen by a model from the catalogue record and the start of the OCR.Values citywide, neighbourhoods, not San Francisco, regional, site |
| hoods | VARCHAR[] | yes | none | as is | Neighbourhoods (from the map's fixed list) the document is about, chosen by a model from the catalogue record and the start of the OCR. |
| streets | VARCHAR[] | yes | none | as is | Streets the document is about, chosen by a model from the catalogue record and the start of the OCR. |
| places | VARCHAR[] | yes | none | as is | Named sites or facilities the document is about (at most 4), chosen by a model from the catalogue record and the start of the OCR. |
| evidence | VARCHAR | yes | free text | private people's names withheld under the embargo | Short quote (<= 160 characters) from the title or text showing what the document is about, picked by a model. |
| identifier | VARCHAR | yes | none | as is | archive.org identifier of the document. |
| run_id | VARCHAR | no | none | as is | dl-tags-haiku55-2026-10 (see runs).Values dl-tags-haiku55-2026-10 |
| seq | BIGINT | yes | none | as is | Line number of the row in the run's tags file. |
Privacy: what kind of text the column holds. Public copy: what the published file does with it; the embargo covers records after 1951.
Preview
| about_sf | doc_type | scope | hoods | streets | places | evidence | identifier |
|---|---|---|---|---|---|---|---|
| false | plan | regional | [] | [] | [] | Proposed Final Bay Area '94 Clean Air Plan ... Prepared by… | C123309161 |
| false | plan | regional | [] | [] | [] | Bay Area Air Quality Plan prepared by ABAG, BAAQMD and MTC… | c124892754 |
| true | study or report | regional | [] | [] | [] | EVALUATION REPORT: THE IMPACT AND PERFORMANCE OF AFFIRMATI… | C123318947 |
| true | audit | citywide | [] | [] | [] | Many San Francisco departments, boards, commissions and ot… | C101744619 |
| true | study or report | citywide | [] | [] | [] | A PLAN TO FIX MUNI A Special Report to Mayor Willie L. Bro… | C124921218 |
| true | audit | citywide | [] | [] | [] | Management Audit of the San Francisco Municipal Railway Pr… | C124921892 |
| false | ordinance or legislation | regional | [] | [] | [] | BAY AREA AIR POLLUTION CONTROL DISTRICT ... PROPOSED NEW S… | C123309639 |
| true | study or report | citywide | [] | [] | [] | The Equal benefits ordinance : a six month report. San Fra… | C124910762 |
8 of 10 columns shown. Eight rows sampled at build time. Hover a shortened value for all of it.
Download
| Format | File | Size |
|---|---|---|
| Parquet | x_dl_tags.parquet ↗ | < 0.1 MB |
| SQLite (all tables) | qipu_sf.db ↗ | 6.44 GB |
SQL
SELECT *
FROM x_dl_tags
LIMIT 100
Run in the SQL console (DuckDB in the browser, over the Parquet file).
Python
import duckdb
duckdb.sql("SELECT * FROM 'https://tiles.qipu.org/data/releases/v0.7.1/parquet/x_dl_tags.parquet' LIMIT 5").show()