Skip to main content
Loading navigation
Back to challenges

Cross-Border LEI Entity Resolution Pipeline with LlamaIndex and Jimdo

Cross-border payments are frequently stalled by disjointed Legal Entity Identifier (LEI) records and unverified corporate hierarchy data. Build an entity resolution pipeline using LlamaIndex RAG agents and Jimdo web tooling to consolidate multi-source entity data and match counterparty identities accurately. Reduce unresolved cross-border entity verification failures to under 2%.

CybersecurityHosted by Vera
Sign in free to start

What you are building

Construct an automated cross-border entity resolution system using LlamaIndex and Jimdo tools to parse and verify corporate LEI records.

How work is evaluated

Evaluation

Evaluates accuracy of matching noisy counterparty string inputs to validated LEI entity records.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

exact_lei_match

Verifies matched LEI string matches target exact LEI

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

resolution_recall

Proportion of valid LEI entities successfully resolved • target: 0.98 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

  • Index corporate registry filings and GLEIF records with LlamaIndex vector indices

  • Integrate Jimdo web extraction tools to fetch dynamic company profile web updates

  • Perform fuzzy matching and graph disambiguation on ambiguous legal entity names

  • Generate verifiable entity confidence vectors for payment engine ingestion

Resources

Dataset notes

Dataset of 500 entity records with simulated corporate typos, variations, and missing address components mapped to standard LEIs.

Challenge setup

Evaluates accuracy of matching noisy counterparty string inputs to validated LEI entity records.

Challenge input

JSON containing entity name, address string, jurisdiction code

LlamaIndex

Primary framework for vector retrieval

Jimdo

Web content and identity signal extraction

Evaluated output

JSON containing matched LEI, canonical name, and match confidence

Evaluation checks
  • Verifies matched LEI string matches target exact LEI
  • Proportion of valid LEI entities successfully resolved • target: 0.98 • range: 0-1
Configured evaluation evidence
  • Benchmark: EntityRes-Eval
  • Resolution Recall target: 0.98
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • Llama Index · Required
  • LlamaIndex · Optional
  • Jimdo · Optional

Evaluation contract

  • exact_lei_match · Weight 1
  • resolution_recall · Weight 1

Metrics

  • resolution_recall · Target 0.98

Benchmarks

  • EntityRes-Eval
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing entity name, address string, jurisdiction code

    Output: JSON containing matched LEI, canonical name, and match confidence

    Execution harness: Python

Evaluation tools

  • LlamaIndex · Indexing & RAG Engine
  • Jimdo · Web Scraping Tool

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Cross-Border LEI Entity Resolution Pipeline with LlamaIndex and Jimdo