Turn document text into a graph your agent can cite
Superlinked gives your agent one API to pull the companies, products and relations out of a document, with source offsets behind every node.
Pursuant to the terms of the Merger Agreement, on September 14, 2026, Merger Sub merged with and into Convergent, whereupon the separate corporate existence of Merger Sub ceased and Convergent continued as the surviving corporation and a wholly owned subsidiary of Veracyte (the “Merger”). Convergent is a genomic diagnostics company focused on bladder cancer, and the acquisition adds Convergent’s UroAmp and proprietary urine tumor DNA technology to the Veracyte roadmap.
Pull a typed graph out of a merger agreement or a recall notice
Merger closing
company · subsidiary · agreement · state · date acquired · subsidiary of · incorporated in · party to
On September 4, 2026 (the “Closing Date”), Tarsus Pharmaceuticals, Inc. (the “Company”) completed its previously announced acquisition of Alkeus Pharmaceuticals, Inc., a Delaware corporation (“Alkeus”), pursuant to that certain Agreement and Plan of Merger, dated as of July 31, 2026 (the “Merger Agreement”), by and among the Company, Alkeus, Apex 2026 Merger Sub, Inc., a Delaware corporation and wholly-owned subsidiary of the Company (“Merger Sub”), and Shareholder Representative Services LLC, a Colorado limited liability company solely in its capacity as the securityholders’ representative.
Highlight lands on another mention The edge is true, but the model returned only the Delaware that describes Apex 2026 Merger Sub, so the highlighted span is that later mention.
Returned with no edge September 4, 2026 · Agreement and Plan of Merger · July 31, 2026 · Merger Agreement · Shareholder Representative Services LLC · Colorado
Vehicle recall
vehicle model · component · supplier · automaker · model year equipped with · produced by · contains
Based on the data and test results, the team determined that the issue is specific to the 2020-2022 model year Ford Escape and Lincoln Corsair vehicles equipped with a specific 8” display produced by Japan Display Incorporated (JDI) and containing an Infineon touch Integrated Circuit (IC). Ford reviewed other model lines for this concern and determined this concern may also be present in some 2020-2024 model year Explorer and Aviator vehicles equipped with a 10.1” version of the JDI display with Infineon touch IC.
Returned with no edge 2020-2022 · Ford · Lincoln · Japan Display Incorporated · Infineon touch Integrated Circuit · 2020-2024 · Explorer · Aviator · JDI display · Infineon touch IC
Drug recall
company · parent company · drug product · packaging · location operating company of · recalls · may contain · headquartered in
LAKE ZURICH, Ill.— Fresenius Kabi, an operating company of the Fresenius Group, is voluntarily recalling one lot of Morphine Sulfate Injection USP, Simplist® 2 mg/1 mL due to a label mix-up. The MicroVault labeled as Morphine 2 mg/1 mL, may contain a Prefilled Syringe of Dilaudid 0.5 mg/0.5 mL. This recall is being conducted to the user level.
Not stated in the text LAKE ZURICH is the dateline of the release; the text never names a headquarters.
Returned with no edge Morphine Sulfate Injection USP · MicroVault · Morphine 2 mg/1 mL
Credit agreement
company · bank · agreement · amount · date borrower under · administrative agent of · commitment amount
On April 30, 2026 (the “Closing Date”), Flex Ltd. (the “Company”) entered into a Credit Agreement (the “Credit Agreement”), by and among the Company, as borrower, the lenders party thereto, and Citibank, N.A., as administrative agent, which provides a senior delayed draw term loan credit facility (the “Credit Facility”) in an aggregate commitment amount of $1.45 billion.
Wrong edge The filing makes Citibank administrative agent under the Credit Agreement, not agent of Flex.
Returned with no edge April 30, 2026
10 inputs were recorded and 5 appear on this page. The model returned 11 edges across these four paragraphs and 5 in the graph above; every one is drawn, and a hand review flagged 3 of the 11.
Choose your own entity and relation types on every call
from sie_sdk import SIEClientclient = SIEClient( api_key="API keysk-sie-…", base_url="https://api.superlinked.com",)text = "textLAKE ZURICH, Ill.— Fresenius Kabi, an operating company of the Fresenius Group, is voluntarily recalling one lot of Morphine Sulfate Injection USP, Simplist® 2 mg/1 mL due to a label mix-up. The MicroVault labeled as Morphine 2 mg/1 mL, may contain a Prefilled Syringe of Dilaudid 0.5 mg/0.5 mL. This recall is being conducted to the user level."entities = client.extract( "modelfastino/gliner2-large-v1", {"text": text}, labels=[ "labelcompany", "labelparent company", "labeldrug product", "labelpackaging", "labellocation", ],)relations = client.extract( "modelfastino/gliner2-large-v1", {"text": text, "metadata": {"entities": entities["entities"]}}, labels=[ "labeloperating company of", "labelrecalls", "labelmay contain", "labelheadquartered in", ],)print(entities["entities"])print(relations["relations"])import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient('https://api.superlinked.com', {
apiKey: 'sk-sie-…',
});
const text = "LAKE ZURICH, Ill.— Fresenius Kabi, an operating company of the Fresenius Group, is voluntarily recalling one lot of Morphine Sulfate Injection USP, Simplist® 2 mg/1 mL due to a label mix-up. The MicroVault labeled as Morphine 2 mg/1 mL, may contain a Prefilled Syringe of Dilaudid 0.5 mg/0.5 mL. This recall is being conducted to the user level.";
const entities = await client.extract(
'fastino/gliner2-large-v1',
{ text },
{ labels: ["company","parent company","drug product","packaging","location"] },
);
const relations = await client.extract(
'fastino/gliner2-large-v1',
{ text, metadata: { entities: entities.entities } },
{ labels: ["operating company of","recalls","may contain","headquartered in"] },
);
console.log({ entities: entities.entities, relations: relations.relations });entities=$(curl https://api.superlinked.com/v1/extract/fastino%2Fgliner2-large-v1 \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"items\":[{\"text\":\"LAKE ZURICH, Ill.— Fresenius Kabi, an operating company of the Fresenius Group, is voluntarily recalling one lot of Morphine Sulfate Injection USP, Simplist® 2 mg/1 mL due to a label mix-up. The MicroVault labeled as Morphine 2 mg/1 mL, may contain a Prefilled Syringe of Dilaudid 0.5 mg/0.5 mL. This recall is being conducted to the user level.\"}],\"params\":{\"labels\":[\"company\",\"parent company\",\"drug product\",\"packaging\",\"location\"]}}")
entities_json=$(printf '%s' "$entities" | jq '.items[0].entities')
curl https://api.superlinked.com/v1/extract/fastino%2Fgliner2-large-v1 \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"items\":[{\"text\":\"LAKE ZURICH, Ill.— Fresenius Kabi, an operating company of the Fresenius Group, is voluntarily recalling one lot of Morphine Sulfate Injection USP, Simplist® 2 mg/1 mL due to a label mix-up. The MicroVault labeled as Morphine 2 mg/1 mL, may contain a Prefilled Syringe of Dilaudid 0.5 mg/0.5 mL. This recall is being conducted to the user level.\",\"metadata\":{\"entities\":$entities_json}}],\"params\":{\"labels\":[\"operating company of\",\"recalls\",\"may contain\",\"headquartered in\"]}}"Build the "Knowledge graph" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: fastino/gliner2-large-v1 (SIE primitive: /extract). Keep the model id configurable.
Task
- Input: a block of text.
- Behaviour: return the entities and the relations between them as a graph
- Use the two /extract calls shown in the SDK snippet: extract entities first, then pass them as item metadata while extracting relations.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.operating company ofFresenius GrouprecallsSimplist® 2 mg/1 mLheadquartered inLAKE ZURICHlocation0:11company19:33parent company63:78drug product116:146drug product148:167packaging195:205drug product217:235Knowledge graph quality and latency
Deploy your way
Managed Cloud
Full compute toolkit for your agents with zero ops.
- No idle GPUs, pay for what you use
- Fits your stack: SDK, API, CLI, MCP
- Zero lock-in, self-host the same stack
- SOC 2 Type 2, US or EU data residency
no credit card required
Self-host with K8s
Easy & scalable deployment in your own cloud.
- Terraform to your cloud in minutes
- Apache-2.0, same engine as Cloud
- Scales to zero, no bill between jobs
- Per-tenant pools, no noisy neighbors
Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our GCP project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our Azure AKS cluster via helm install. Requirements: superlinked.com/docs/deployment Run locally
Run the same models on your own machine.
- Runs on NVIDIA GPU or Apple Silicon
- One command, no Docker or cluster
- All 100+ Cloud models, fully offline
- Same SDK and IDs, no code changes
pip install "sie-server[local]" && sie-server servepip install "sie-server[local]" && sie-server serve --device cuda