Knowledge bases and reference vocabularies for research

Reference work depends on authoritative identifiers: a standard term for a material, a stable id for a language, a canonical record for a person or a recording. Kahubi connects to Wikidata and Wikipedia, the Getty Art & Architecture Thesaurus, Thesaurus of Geographic Names and Union List of Artist Names, Glottolog for the world’s languages, the OEIS for integer sequences, MusicBrainz for music and Project Gutenberg for public-domain texts.

Use them to normalise names and terms in a dataset, give background before you turn to primary sources, or check a fact against a curated record. Answers cite Q-ids, AAT and TGN ids, glottocodes and A-numbers.

7 sources you can connect

Questions researchers ask these sources

  • “Find the passages in A Vindication of the Rights of Woman where Wollstonecraft discusses the education of girls.”

    The book record and the relevant passages from the public-domain text.

    Project Gutenberg
  • “What is the preferred Art & Architecture Thesaurus term for "tempera", and what is its scope note?”

    The AAT concept with id, preferred label and scope note, so catalogue entries use consistent terms.

    Getty Vocabularies
  • “Which sequence starts 1, 2, 5, 14, 42, 132, and what does it count?”

    The A-number (Catalan numbers), its definition, formulas and key references.

    OEIS
  • “Resolve these 40 historical place names to Wikidata items with coordinates.”

    QIDs, labels and coordinates, with ambiguous names flagged for you to decide.

    Wikidata
  • “Give me a short background on the Swedish welfare state model and the primary sources the Wikipedia article cites.”

    A summary of the article with its section list, and the references it points to so you can cite those instead.

    Wikipedia
  • “How is Meänkieli classified, and what is its ISO 639-3 code?”

    The languoid’s glottocode, ISO code, classification tree and coordinates.

    Glottolog

Frequently asked questions

Should I cite Wikipedia?
Usually not directly. The assistant uses Wikipedia for orientation and points you to the primary sources the article cites, which are what you should reference.
Can it run SPARQL queries?
Yes. For Wikidata and the Getty vocabularies the assistant can write and run SPARQL for you, which is useful for building lists or linking a dataset to standard identifiers.
What is a knowledge base useful for in a thesis?
Consistent terminology and identifiers: the same term for the same concept throughout, place names linked to a gazetteer, and people or works matched to a stable record.

How MCP grounds AI answers in real records

Search knowledge bases sources in one research chat

Free to start. Connect a source in one click and get answers that cite the records they came from.