Extractions Viewer

← Back

About

The Philosophical Transactions of the Royal Society is the longest-running scientific journal in the world, with its first volume appearing in 1665. As part of the Secrets to Patent project, we use local LLMs to extract structured information from OCR'd article text: whether each article describes an experiment, what locations are mentioned, and who participated.

This viewer lets you browse those extractions article by article, filter by classification (experiment: yes / no / unsure), and inspect extracted locations and participants alongside the original article text.

Dashboard

The collapsible band at the top of the page is a small dashboard for exploring the corpus as a whole. The timeline shows three series per year: number of articles, average number of detected locations per article, and average number of detected participants per article. The two histograms on the right show the per-article distribution of detected locations and detected participants — both visibly power-law, with most articles in the low bins and a long tail.

Every chart is brushable: click and drag along the x-axis to select a range. All brushes AND together with the experiment dropdown and immediately re-filter the article list and the other charts. The reset filters link clears every active brush at once, and − Charts hides the dashboard for full-height article view.

URL routing

The full filter state is encoded in the URL fragment, so any view is bookmarkable and shareable. Open #article=1290791 to jump straight to a single article, or combine keys to share a filtered slice: #article=1290791&years=1700-1750&locs=2-&parts=1-3&exp=yes. Open-ended ranges (locs=2-, years=-1750) are accepted.

Prompt

Each article was passed to the LLM with the following prompt. Structured output was enforced via JSON schema using the Ollama API.

You are analysing an article from the Philosophical Transactions of the Royal Society (17th–19th century). Answer three questions:

1. is_experiment: Does this article describe one or more experiments or systematic observations? Answer "yes", "no", or "unsure".

2. locations: List every spatial location where an experiment or observation took place. For each, provide:
   - place: the immediate setting at room or building scale (e.g. "private study", "ship's cabin", "kitchen"); null if not mentioned
   - geography: named place at city, region, country, estate, or vessel scale (e.g. "London", "aboard HMS Endeavour"); null if not mentioned
   - detail: specific spatial detail within the place (e.g. "by the south window", "in a dark corner"); null if not mentioned
Do not include apparatus or containers as locations. Return an empty list if no spatial setting is mentioned.

3. participants: List every person named in the article who conducted, observed, or contributed to the experiment or observation. For each, provide:
   - name: the person's name as it appears in the text
   - role: their role if stated (e.g. "experimenter", "observer", "subject", "correspondent", "author"); null if not clear
Return an empty list if no individuals are named.

Repository

Source code and data: github.com/DigitalHistory-Lund/SecToPat-PhilTransExtractions

Team

Natacha Klein Käfer is the principal investigator of the Secrets to Patent project. The extraction pipeline and viewer were assembled by Mathias Johansson using Python, Ollama, and Claude.

Citation

If you use this site or its data in your work, please cite the repository. Machine-readable metadata is in CITATION.cff.

License

CC BY-NC 4.0 This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). See LICENSE.

Contact

For questions or feedback, contact Mathias Johansson at MathiasJohansson@kultur.lu.se, or open an issue.