Our entity fact companion journal 858

Lead Story · OCT 2

Selected Fact Retrieval in MCP for Google Knowledge Graph and Wikidata

Teams that work with entity data usually hit the same wall sooner or later. Search is easy enough. Reliable retrieval is not. You can find ten plausible entities for a name like "Mercury" in seconds, but narrowing that result to the right record, extracting only the facts you need, and preserving enough evidence for later review is where systems often become messy. That is the problem space where the open source project commonly described as Wikidata + Google Knowledge

Continued inside

Read the full column

Analysis · OCT 2

How MCP for Wikidata Avoids Overclaiming Identity Matches

Entity resolution looks easy right up until it starts making confident mistakes. Anyone who has worked with catalogs, research datasets, CRM exports, media archives, or public knowledge bases has seen the same pattern. Two records share a name, a rough description, maybe even an occupation, and a system eagerly decides they are the same thing. That kind of shortcut is seductive because it keeps workflows moving. It is also exactly how bad links get embedded into downstre

Dispatch · OCT 2

Understanding Candidate Evidence in MCP for Wikidata

When people talk about entity resolution against Wikidata, they often jump straight to the happy path: search a name, grab a QID, move on. In practice, that is where mistakes start. The hard part is rarely finding a candidate. The hard part is deciding whether the candidate is good enough to trust, whether the evidence is thin, and whether uncertainty should stop the workflow. That is why candidate evidence matters so much in the emerging tooling around MCP for Wikida

Also in the edition

How MCP for Google Knowledge Graph and Wikidata Uses Exact ID Joins

When teams talk about entity resolution, they often jump straight to fuzzy matching, embeddings, or ranking models. Those methods have their place, but they also create a recurring problem: people start trusting confidence scores they cannot really inspect. The more records you process, the more expensive those blind spots become. A mistaken join between two public figures, two companies with similar names, or two places that changed names over time can ripple through searc

OCT 2

AUTO_MATCH, HOLD, AMBIGUOUS, and NO_CANDIDATE in MCP for Wikidata

Entity resolution looks simple until you have to trust it. Anyone who has tried to map a local catalog, CRM, newsroom archive, research database, or product knowledge base to Wikidata knows where the pain starts. Names collide. Labels are incomplete. Dates are missing. Places change names. Organizations merge, split, or rebrand. A human can often sense the difference between a plausible match and a dangerous one. Software needs firmer rules. That is what makes the res

OCT 2

A Closer Look at Inspectable Evidence in MCP for Wikidata

The most interesting thing about recent tooling around Wikidata is not that it helps a model find an entity faster. Search speed is useful, but it is not the hard part. The hard part is trust. If an agent links a person, company, place, or work to the wrong Wikidata item, the mistake does not stay local. It tends to spread into downstream records, summaries, and decisions. That is why inspectable evidence matters. A good MCP server for knowledge work should do more than

OCT 2

A Guide to Record Linking With MCP for Wikidata

Record linking sounds straightforward until you have to do it at scale. A spreadsheet says “Springfield College,” another says “Springfield Coll.,” a third uses a local code that only made sense to the team that built the database fifteen years ago. Somewhere in that mess is a real entity that should map to a stable identifier, but getting there takes more than string matching. That is why the recent appearance of an MCP server and CLI for Wikidata and Google Knowledge G

OCT 1