> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gdeltcloud.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Filer relations (LLM)

> Subsidiary / supplier / customer / jurisdiction edges for a filer, derived from filing text through GDELT Cloud's proprietary AI pipeline and resolved to entity_ids with evidence. Requires a plan with SEC filings access (`can_use_filings`) — the Corporate & Supply Chain plan and above.



## OpenAPI

````yaml /api-reference/openapi-v2.json get /api/v2/filings/{cik}/relations
openapi: 3.0.3
info:
  title: GDELT Cloud API v2
  version: 2.0.0
  description: >-
    Clean v2 REST API for generated GDELT Cloud structured Events, clustered
    Stories, linked Entities, summaries, admin1 discovery, significance ranking,
    and paginated article evidence.


    Event significance is a family-scoped weighted blend, renormalized so every
    event family spans a true 0-1: each event's raw total is divided by the
    maximum its own family can reach (Conflict 1.00, CAMEO+ POLITICAL 0.90,
    other CAMEO+ domains 0.65). All events: Goldstein severity 0.25, article
    evidence 0.05, confidence 0.05. Conflict only: fatalities 0.55 (log-scaled
    by body count) and civilian targeting 0.10. CAMEO+ only: magnitude 0.20,
    systemic importance 0.15, propagation potential 0.10, market sensitivity
    0.10. When magnitude is unmeasured its term AND its 0.20 weight are both
    dropped. The four CAMEO+ metrics are rubric scores produced by published
    formulas - ordinal ranking signals, not measurements, probabilities, or
    predicted price moves. goldstein_scale is one canonical public metric,
    populated for Conflict Events and CAMEO+ POLITICAL Events where meaningful.
    Story linked_event_count is a Story-to-Event link aggregate, not a distinct
    Event total.
servers:
  - url: https://gdeltcloud.com
    description: Production
  - url: http://localhost:3000
    description: Local development
security:
  - ApiKeyAuth: []
tags:
  - name: Events
    description: Coded CAMEO+ / conflict events — search, fetch, and summarize.
  - name: Stories
    description: Clustered narratives (stories) and their articles.
  - name: Entities
    description: >-
      People & organizations — resolve a name to an entity, then fetch its
      profile and tone.
  - name: Geography
    description: Admin-1 geography lookups.
  - name: Energy
    description: Global Energy Monitor assets + ownership registry.
  - name: Facilities
    description: >-
      Unified physical-asset directory — GEM energy assets + World Port Index
      ports + Epoch AI data centers on one keyed surface, resolved to spine
      owners. Plan-gated (Analyst plan and up).
  - name: Screening and Reference
    description: >-
      Restricted-party lists, screening, and ownership-chain exposure.
      Plan-gated (`can_use_screening` / `can_use_exposure`).
  - name: China
    description: >-
      China overseas development finance (AidData GCDF). Plan-gated
      (`can_use_china`).
  - name: Media Intelligence
    description: >-
      Entity tone (`can_use_tone`) and Share of Voice (`can_use_share_of_voice`)
      are plan-gated. Social signal remains an admin-only preview.
  - name: Filings
    description: >-
      SEC EDGAR filings, XBRL financials, and AI-extracted relations. Requires a
      plan with SEC filings access (`can_use_filings`) — the Corporate & Supply
      Chain plan and above.
  - name: Macro Finance
    description: >-
      FRED economic time series (catalog, point-in-time observations, releases).
      Plan-gated (`can_use_macro`).
  - name: Maritime
    description: >-
      AIS-derived vessel-flow signals across maritime chokepoints — chokepoint
      transits, last-known vessel positions, carriers, dwell, and AIS-dark gaps.
      Plan-gated (`can_use_maritime`).
  - name: Briefs
    description: Source-backed monitoring briefs.
paths:
  /api/v2/filings/{cik}/relations:
    get:
      tags:
        - Filings
      summary: Filer relations (LLM)
      description: >-
        Subsidiary / supplier / customer / jurisdiction edges for a filer,
        derived from filing text through GDELT Cloud's proprietary AI pipeline
        and resolved to entity_ids with evidence. Requires a plan with SEC
        filings access (`can_use_filings`) — the Corporate & Supply Chain plan
        and above.
      operationId: get-filer-relations-v2
      parameters:
        - name: cik
          in: path
          required: true
          schema:
            type: integer
          description: SEC CIK number.
        - name: rel_type
          in: query
          required: false
          schema:
            type: string
            enum:
              - subsidiary
              - supplier
              - customer
              - counterparty
              - partner
              - jurisdiction_exposure
              - risk_factor
          description: >-
            Filter to one relation kind: subsidiary | supplier | customer |
            counterparty | partner | jurisdiction_exposure | risk_factor (Item
            1A risk themes). Omit for all.
        - name: country
          in: query
          required: false
          schema:
            type: string
            example: Vietnam
          description: >-
            Filter to relation edges whose counterparty (object) jurisdiction
            matches this country — useful on `jurisdiction_exposure` edges.
            Accepts a country name (`Vietnam`), ISO-2 (`VN`), or ISO-3 (`VNM`)
            via the shared `resolveCountryInput` layer, matched against the
            edge's `object_country_iso3`; an unresolvable value returns `400
            INVALID_COUNTRY`.
        - name: limit
          in: query
          required: false
          schema:
            type: integer
            default: 50
            maximum: 200
          description: Rows per page (1–200).
        - name: cursor
          in: query
          required: false
          schema:
            type: string
          description: Pagination cursor (opaque offset).
      responses:
        '200':
          description: >-
            A page of LLM-extracted relation edges, by rel_type then confidence.
            Each row: rel_type, source, subject_name, object_name,
            object_country_iso3, object_commodity, ownership_pct (or null),
            evidence (supporting quote), resolved_entity_id (entity-spine id,
            when resolved), confidence (0–1), model (extraction model version),
            accession_no. Envelope: { success, cik, data, pagination,
            applied_filters }.
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                  cik:
                    type: integer
                  data:
                    type: array
                    items:
                      type: object
                      properties:
                        relation_uid:
                          type: string
                        rel_type:
                          type: string
                        source:
                          type: string
                        subject_name:
                          type: string
                        object_name:
                          type: string
                        object_country_iso3:
                          type: string
                        object_commodity: {}
                        ownership_pct:
                          type: integer
                        amount_usd: {}
                        amount_text: {}
                        pct_value: {}
                        evidence:
                          type: string
                        resolved_entity_id:
                          type: string
                        confidence:
                          type: number
                        model:
                          type: string
                        accession_no:
                          type: string
                  pagination:
                    type: object
                    properties:
                      limit:
                        type: integer
                      cursor: {}
                      next_cursor: {}
                  applied_filters:
                    type: object
                    properties:
                      cik:
                        type: integer
                      ignored:
                        type: object
                        properties: {}
              examples:
                example:
                  summary: GET /api/v2/filings/{cik}/relations — example response
                  value:
                    success: true
                    cik: 65270
                    data:
                      - relation_uid: a1b2c3d4e5f60718293a4b5c6d7e8f90
                        rel_type: subsidiary
                        source: ex21
                        subject_name: Methode Electronics, Inc.
                        object_name: Hetronic Germany GmbH
                        object_country_iso3: DEU
                        object_commodity: null
                        ownership_pct: 100
                        amount_usd: null
                        amount_text: null
                        pct_value: null
                        evidence: >-
                          Hetronic Germany GmbH (Germany) — 100% owned, included
                          in the list of subsidiaries filed as Exhibit 21.1 to
                          this Annual Report on Form 10-K.
                        resolved_entity_id: ent_4d9a2f31c7b8
                        confidence: 0.97
                        model: gpt-5.4-nano:ex21:v1
                        accession_no: 0000065270-26-000041
                      - relation_uid: f0e9d8c7b6a51403928f7e6d5c4b3a21
                        rel_type: supplier
                        source: item1
                        subject_name: Methode Electronics, Inc.
                        object_name: Taiwan Semiconductor Manufacturing Company
                        object_country_iso3: TWN
                        object_commodity: semiconductors
                        ownership_pct: null
                        amount_usd: 84000000
                        amount_text: approximately $84 million
                        pct_value: null
                        evidence: >-
                          We source a significant portion of our
                          application-specific integrated circuits from foundry
                          partners in Taiwan, and a disruption in that supply
                          could materially affect our Automotive segment.
                        resolved_entity_id: ent_2b7c9e14a6d3
                        confidence: 0.84
                        model: gpt-5.4-mini:item1:v1
                        accession_no: 0000065270-26-000041
                    pagination:
                      limit: 50
                      cursor: null
                      next_cursor: null
                    applied_filters:
                      cik: 65270
                      ignored: {}
        '401':
          description: Missing/invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Plan required (PLAN_REQUIRED)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      security:
        - ApiKeyAuth: []
components:
  schemas:
    ErrorResponse:
      type: object
      properties:
        success:
          type: boolean
          enum:
            - false
        error:
          type: string
        code:
          type: string
        details:
          type: object
          description: >-
            Recoverable validation context when available, such as param,
            invalid_value, accepted_values, nearest_values, and a corrected
            example.
          additionalProperties: true
  securitySchemes:
    ApiKeyAuth:
      type: http
      scheme: bearer
      bearerFormat: gdelt_sk_...
      description: 'GDELT Cloud API key. Send as `Authorization: Bearer gdelt_sk_...`.'

````