Kernel.ai: Kernel Resolve Entity

Match a company from its name, website, address, email or phone to one canonical company record.

Tool ID: kernel_resolve_entity

Run this action

Use the TypeScript SDK for one call. Use ctx.tools.execute(...) inside a Play for durable calls, scheduled calls, or CSV processing.

import { Deepline } from 'deepline';

const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
  'kernel_resolve_entity',
  {
    "legal_name": "Example",
    "trading_name": "Example",
    "website": "https://example.com"
  },
);

console.log(result.toolResponse.raw);

CLI

deepline tools execute kernel_resolve_entity --input '{
  "legal_name": "Example",
  "trading_name": "Example",
  "website": "https://example.com"
}' --json

Example response

The SDK returns this shape at result.toolResponse.raw. The example values illustrate the response.

{
  "data": {
    "id": "id_123",
    "status": "processing"
  }
}

Use deepline describe kernel_resolve_entity --json for the latest machine-readable contract.

Input reference

Starts an entity resolution job for a company. Returns immediately with an id — poll GET /v1/entity-resolution/{job_id} until the status is completed.

Name	Type	Required	Default	Details
`payload.legal_name`	`string`	No	—	Registered legal name of the company (e.g. “Stripe, Inc.”) Minimum length: 1.
`payload.trading_name`	`string`	No	—	Primary brand or trading name (e.g. “Stripe”) Minimum length: 1.
`payload.website`	`string`	No	—	Company website URL. Minimum length: 1.
`payload.country`	`string`	No	—	Country name or ISO 3166-1 alpha-2 code. Minimum length: 1.
`payload.city`	`string`	No	—	City. Minimum length: 1.
`payload.state`	`string`	No	—	State or province. Minimum length: 1.
`payload.postal_code`	`string`	No	—	ZIP or postal code. Minimum length: 1.
`payload.address`	`string`	No	—	Street address. Minimum length: 1.
`payload.email`	`string`	No	—	Email address. Only the domain portion is used for matching. Minimum length: 1.
`payload.phone`	`string`	No	—	Phone number. Used as an additional signal for entity resolution. Minimum length: 1.
`payload.external_id`	`string`	No	—	Your own identifier for this record. Minimum length: 1.
`payload.kernel_id`	`string`	No	—	An existing Kernel ID. When provided, the resolver skips matching and returns the canonical record for this entity. Minimum length: 1.
`payload.linkedin_url`	`string`	No	—	LinkedIn URL for the company (e.g. “https://linkedin.com/company/stripe”). Used as an additional signal for entity resolution. Minimum length: 1.
`payload.match_to_linkedin`	`boolean`	No	`false`	When `true`, Kernel will attempt to match the resolved entity to a LinkedIn company profile. The result is returned in the `linkedin` field of the completed record. Defaults to `false`.
`payload.identity_bias`	`"NAME_BIAS" \| "URL_BIAS"`	No	—	Bias the resolver toward name or URL matching when they conflict. One of: `NAME_BIAS`, `URL_BIAS`. Defaults to `URL_BIAS`. Allowed: `NAME_BIAS`, `URL_BIAS`.

Output reference

Standard tool result payload.

Name	Type	Required	Default	Details
`result.data`	`object`	Yes	—	Provider response payload.
`result.data.id`	`string`	Yes	—	Unique identifier for the created job.
`result.data.status`	`"processing"`	Yes	—	Initial status of the job. Allowed: `processing`.
`result.meta`	`object`	No	—	Additional response metadata (status, paging).

Deepline cost

Pricing model: fixed (per call).
Estimated Deepline credits: 1.4 per pricing unit.

​Run this action

​CLI

​Example response

​Input reference

​Output reference

​Deepline cost

​Related documentation

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

Related documentation