← Research

Research note · July 17, 2026

LinkedCulture just crossed 500,000 objects.

The unified semantic index now spans 500,000+ open-access records across nine museums, from the Rijksmuseum to the Minneapolis Institute of Art.

linkedcultureculturalheritagemuseumtechopenaccessdigitalhumanitiessemanticsearchvectorsearchmuseumcollections


LinkedCulture just crossed 500,000 objects.

The unified semantic index now holds more than 500,000 open-access museum records, up from 300,000 in June. The growth this round came from three collections in particular: the Rijksmuseum (112,510), the Getty (108,156), and the Met (still climbing past 86,000 as this posts).

They join the Art Institute of Chicago, Paris Musées, the Cleveland Museum of Art, the Minneapolis Institute of Art, Harvard Art Museums, and a growing Joconde set from the French Ministry of Culture, for nine institutions total in one cross-collection semantic map.

500,203 objects across nine museums, ranked by size
500,203 objects across nine museums, ranked by size

Getting here wasn't just a matter of raising a limit. Along the way this round turned up a museum source whose parser had been silently producing zero new records, a dedup check comparing against a Qdrant collection that no longer existed, and the Met's API blocking the server's IP after sustained fetching, same as before.

None of that is visible in the number. What's visible is that a Persian textile at the Art Institute now sits beside its kin at the Met and the Rijksmuseum, discoverable in a single search that crosses institutions, collections, and languages.

Every object still links back to its home museum. The canonical record always stays with the institution that holds it. LinkedCulture doesn't replace any museum's catalogue, it surfaces the relationships between what they hold.

Explore it: https://linkedculture.org/

The research behind this series is documented in several papers:

Paper 1: Discovery architecture for cultural heritage: layered retrieval, institutional authority, and the limits of keyword search https://linkedculture.org/research/discovery-architecture-for-cultural-heritage

Paper 2: Embedding cultural heritage metadata https://linkedculture.org/research/embedding-cultural-heritage-metadata

Paper 3: Semantic Clusters and Language Partitioning in a Multi-Institutional Cultural Heritage Index https://linkedculture.org/research/semantic-clusters-language-partitioning

Learn more about LinkedCulture and the work behind it: https://linkedculture.org/