companies_v2.entity_kind — the taxonomy landed via tasks #336 (deterministic classifier) + #339 (Qwen-classify the unknown tail).
The previous flat coverage numbers ("96% of companies missing description")
were misleading. Two-thirds of companies_v2 rows are
sec_shell_unknown — SEC filing shells with no operating business,
where a missing website or description isn't a gap, it's the correct
absence. This report breaks coverage down by what an entity actually is.
Percentages are share of rows within that entity_kind with the field populated. Colors: ≥80% populated, 40-80%, 10-40%, <10%.
| Entity kind | Rows | % total | Domain | Description | Industries | Country | City | State | Founded | Employees | Ticker | CIK | Deals | Atlas |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Operating co (rich) | 84,015 | 9.3% | 74% | 66% | 41% | 69% | 28% | 26% | 2% | 0% | 6% | 13% | 71% | 0% |
| Operating co (thin — domain only) | 27,195 | 3.0% | 100% | 0% | 0% | 97% | 94% | 94% | 0% | 0% | 2% | 94% | 0% | 0% |
| Operating co (no domain, has deals) | 7,392 | 0.8% | 0% | 49% | 5% | 24% | 0% | 0% | 0% | 0% | 0% | 1% | 88% | 0% |
| Investment vehicle | 191,667 | 21.2% | 0% | 0% | 1% | 14% | 13% | 13% | 0% | 0% | 0% | 87% | 0% | 0% |
| Foundation / nonprofit | 18,453 | 2.0% | 0% | 0% | 1% | 1% | 0% | 0% | 0% | 0% | 0% | 0% | 0% | 0% |
| SPAC / blank-check | 4,774 | 0.5% | 7% | 5% | 5% | 33% | 7% | 6% | 0% | 0% | 6% | 44% | 8% | 0% |
| Individual (person) | 728 | 0.1% | 0% | 0% | 15% | 5% | 0% | 0% | 0% | 0% | 0% | 0% | 0% | 0% |
| Regulatory body | 1,569 | 0.2% | 0% | 0% | 8% | 32% | 0% | 0% | 0% | 0% | 0% | 0% | 0% | 0% |
| SEC shell (CIK only) | 563,735 | 62.3% | 0% | 0% | 0% | 23% | 23% | 23% | 0% | 0% | 0% | 100% | 0% | 0% |
| Unknown (residual) | 5,631 | 0.6% | 0% | 0% | 10% | 12% | 0% | 0% | 0% | 0% | 0% | 0% | 0% | 0% |
Operating company (rich) = the target class for CB/PB-style consumer surfaces. If we want to compare to their coverage, use these rows' column percentages, not the whole-table flat number.
SEC shell (CIK only) = 63% of rows but correctly has 0% coverage on domain / description / industries / country. These are Form D filers, private-fund vehicles, etc. — they exist to file SEC forms, not to have a web presence. They contribute to the total row count but not to any "gap" a consumer would care about.
Investment vehicle = RIA firms, wealth-management LLCs, family offices, capital partners. High CRD coverage expected; low funded_year expected (they're mostly private RIAs the extractor doesn't have birth-date signal on).
Individual / regulatory body = detection classes surfaced
by Qwen this session. These are things that were previously in the
unknown bucket that shouldn't have been minted as companies at
all. Tail work for a future cleanup pass — either delete from
companies_v2 or migrate to the correct entity table.
operating_company row + column of interest. For a consumer
targeting real operating businesses, operating_company (rich)
+ operating_company_thin + op_co_no_domain
combined = the addressable universe. Sum those n's, then average their
field percentages for the true "operating universe coverage" number.
Task #336 shipped the deterministic classifier (SQL trigger, ~85% coverage
from row-local signals). Task #339 shipped the Qwen residual — 45,499 rows
Qwen-classified out of the ~50K unknown tail, methodology
entity-kind-qwen-v1, every decision reversible via
identity_decisions_v2. ~5,600 rows still in the residual (~9
Inferno chunks still trickling in as of report generation).