Wikidata
A centralized structured-data repository linked to Wikipedia where a single data point can be updated once and automatically propagate across all language versions.
As defined in Jimmy Wales
Where it comes up · 2
Most important claims · 10 of 11Search all claims for “Wikidata” →
- Google and Wikipedia/Wikidata provided different answers about the birthplace of Croatian actress Ena Begović, with Wikipedia claiming Split while the correct answer is likely Trpanj, demonstrating how knowledge ecosystems can become contaminated when sources copy from each other.The Future of Knowledge Graphs in a World of Large Language Models
- ChatGPT cannot reliably determine what it knows versus doesn't know; when asked about mayors born after 1998 (making them younger than 23 at ChatGPT's 2021 knowledge cutoff), it correctly noted this was implausible, but when asked in different ways or via BingChat, it claimed no knowledge of such mayors despite them existing in Wikidata.The Future of Knowledge Graphs in a World of Large Language Models
- Augmented language models (like Toolformer and ChatGPT plugins) can enrich large language models with additional systems that are efficient at specific tasks like math, function calls from Wikifunctions, or fact lookup in knowledge graphs like Wikidata.The Future of Knowledge Graphs in a World of Large Language Models
- Wikidata and similar knowledge graphs should introduce a third special value: 'it's complicated,' to explicitly mark cases where answers cannot be stated with current knowledge graph expressivity, preventing dangerous or wrong answers and flagging areas where LLMs should be trusted instead.The Future of Knowledge Graphs in a World of Large Language Models
- ChatGPT's SPARQL query for Croatian actors had a subtle error—it returned actors born in places within Croatia rather than Croatian actors—and when executed against Wikidata found 445 results, with 154 (one-third) born in Zagreb, providing the conditional probability basis for ChatGPT's guess of Zagreb as Ena Begović's birthplace.The Future of Knowledge Graphs in a World of Large Language Models
- ChatGPT can generate SPARQL queries for knowledge graph databases like Wikidata with correct QIDs (identifiers) with zero-shot learning, and can even generate tables of EU member countries with their correct QIDs, demonstrating memorized knowledge of thousands of structured identifiers.The Future of Knowledge Graphs in a World of Large Language Models
- Answering a six-token question with a 60-token ChatGPT response costs approximately 50 times more than answering via Wikidata query service; a thousand queries cost $7.56 via GPT-4 Azure pricing versus 14 cents for Wikidata cloud hosting.The Future of Knowledge Graphs in a World of Large Language Models
- ChatGPT runs on the fastest and most expensive hardware you can buy, Google runs on the fastest and most expensive hardware you cannot buy, and Wikidata runs on 'abandonware on a server somewhere', illustrating different scales of infrastructure investment.The Future of Knowledge Graphs in a World of Large Language Models
- ChatGPT took about 5 seconds to answer the query 'Who created the School of Athens?' including nearly 1 second for parsing, while Google took 0.5 seconds including parsing and results retrieval, and Wikidata took about 0.25 seconds to generate the answer.The Future of Knowledge Graphs in a World of Large Language Models
- Wikidata realizes an early vision where a single piece of data—like the population of New York City from the decennial census—can be updated in one place and automatically propagate across all language versions of Wikipedia that link to it.Jimmy Wales