Sold by: Sigmodata
Deployed on AWS
Free Trial
Extract named entities from English text, including your own custom types at inference with no retraining. Runs inside your AWS account on CPU, so no text is sent to a third-party API. 18 default entity types.
Overview
Image
Python predict
Image
POST /invocations
Runs inside your own AWS account: your text is processed on a SageMaker endpoint you control, inside your VPC, and is never sent to a third-party API.
This SageMaker model package provides a REST API to detect named entities in US English text. Send a JSON array of sentences and receive labeled spans with character offsets and confidence scores.
Eighteen entity types are detected by default (person, organization, location, date, money, and more). Pass an optional "labels" array to extract any entity types you need (drugs, statutes, tickers) without retraining.
GPU is optional. Deploy on a GPU instance (for example ml.g4dn.xlarge) for higher throughput; the same image uses CUDA automatically when a GPU is present, and falls back to CPU otherwise. The API accepts JSON or CSV and supports real-time endpoints and SageMaker batch transform.
We welcome your feedback at support@sigmodata.com . Usage notebook: https://colab.research.google.com/drive/1iL1Q0FiYfKoUqYzglpeBFDxzDjV8IF9s
Use cases: redacting or routing documents by the people, companies and places they mention, enriching support tickets and contracts with structured fields, and feeding entity data to search, analytics and compliance workflows.
Known limitations: English text only. Event, facility and product are the least accurate default types, and very long inputs should be split into sentences or short paragraphs.
Model and training data
GLiNER medium (urchade/gliner_medium-v2.1), fine-tuned on a sample of Few-NERD (Ding et al., ACL-IJCNLP 2021) plus Sigmodata's own synthetic and hard-negative examples. The container runs in network isolation, so no data leaves your account.
Measured performance
- Span-level micro F1 of 0.956 (precision 0.960, recall 0.952) on our validation set. An entity counts as correct only on an exact character-span and label match.
- F1 by type: 0.97 or higher for person, location (GPE), date, time, money, percent, quantity, ordinal, cardinal and language; 0.90 to 0.96 for organization, group (NORP), law, work of art and non-GPE location; 0.84 to 0.86 for event, facility and product.
- Dates, times, money, percentages, quantities, ordinals and numbers are extracted by deterministic rules rather than the model.
- Throughput about 7 texts per second on ml.m5.xlarge at a batch size of 25.
Highlights
- Extract 18 default entity types (people, organizations, dates, money and more), or pass your own labels per request with no retraining
- Runs inside your own AWS account and VPC - text is never sent to a third-party API
- Span-level F1 of 0.956 on our validation set (exact span and label match); about 7 texts per second on ml.m5.xlarge
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 5 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g4dn.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g4dn.xlarge instance type, real-time mode | $0.10 |
ml.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $0.10 |
ml.c4.2xlarge Inference (Batch) | Model inference on the ml.c4.2xlarge instance type, batch mode | $0.10 |
ml.c4.2xlarge Inference (Real-Time) | Model inference on the ml.c4.2xlarge instance type, real-time mode | $0.10 |
ml.c4.4xlarge Inference (Batch) | Model inference on the ml.c4.4xlarge instance type, batch mode | $0.10 |
ml.c4.4xlarge Inference (Real-Time) | Model inference on the ml.c4.4xlarge instance type, real-time mode | $0.10 |
ml.c4.8xlarge Inference (Batch) | Model inference on the ml.c4.8xlarge instance type, batch mode | $0.10 |
ml.c4.8xlarge Inference (Real-Time) | Model inference on the ml.c4.8xlarge instance type, real-time mode | $0.10 |
ml.c4.xlarge Inference (Batch) | Model inference on the ml.c4.xlarge instance type, batch mode | $0.10 |
ml.c4.xlarge Inference (Real-Time) | Model inference on the ml.c4.xlarge instance type, real-time mode | $0.10 |
Dimensions summary
You pay by the hour for the SageMaker instance that runs this named entity detection model. Pricing scales with the compute you choose, not a subscription. Each instance family offers several sizes: general-purpose (m4, m5), compute-optimized (c4, c5), and GPU-backed (g4dn, g5, p2, p3). Larger sizes carry more capacity and cost more per hour. Most instances come in two modes: batch mode processes stored data in bulk, while real-time mode serves live requests. A few instances offer only one mode. You run the model inside your own AWS account.
Top-of-mind questions for buyers
One HostHrs is one hour that your chosen SageMaker instance runs the model. Charges accrue per hour while the instance is active. The rate depends on the instance type and size you select. You pay only for the hours used, with no upfront commitment.
Both meter instance-hours the same way. Real-time mode keeps an endpoint running to serve live requests, so you pay for every hour it stays up. Batch mode runs a job over stored data, then stops, so you pay only for the job's run time.
Software charges accrue per hour while the instance runs. A fully stopped instance stops the hourly software charge. A real-time endpoint keeps running until you shut it down, so it continues to accrue hours even when idle. Underlying AWS storage fees may still apply separately.
www.sigmodata.com
Helpful?
Vendor refund policy
No refunds, but you may cancel at any time
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Retrained English GLiNER model (sigmodata-ner-basic-8).
- Fixed the training data: locations, languages and laws were missing, and nationalities were labeled as locations
- Dates, times, money, percentages, quantities, ordinals and numbers now use deterministic rules
- Leading articles ("the") are no longer included in entity spans
- Hard-negative training data for PRODUCT, FAC, ORG, and EVENT, with per-label score floors
- Checkpoint stored in S3, version 20261006T134113Z-a985ba0
- Measured micro F1 0.956 (precision 0.960, recall 0.952) on a 422-sentence internal test set, on the deployed package
Additional details
Inputs
- Summary
A JSON object with an "input" array of strings to tag (or a CSV file, one text per line, for batch transform). Optional "labels" array of entity type names (omit to use the 18 defaults listed at https://www.sigmodata.com/products?product=ner-model ) and optional "threshold" (0-1).
- Input MIME type
- application/json, text/csv
{"input": ["Apple reported $5 million in revenue yesterday in Cupertino"]}
Apple reported $5 million in revenue yesterday in Cupertino
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
input | List of text strings to extract entities from | - | Yes |
labels | Optional types to extract (for example ["drug", "ticker"]). Omit to use the 18 defaults: PERSON, NORP, FAC, ORG, GPE, LOC, PRODUCT, EVENT, WORK_OF_ART, LAW, LANGUAGE, DATE, TIME, PERCENT, MONEY, QUANTITY, ORDINAL, CARDINAL. Definitions: https://www.sigmodata.com/products?product=ner-model | - | No |
threshold | Optional confidence cutoff between 0 and 1 (default 0.6) | - | No |
Resources
Vendor resources
Support
Vendor support
Support contact: Email: support@sigmodata.com Support URL: https://www.sigmodata.com/contact
Support description: Email support@sigmodata.com or https://www.sigmodata.com/contact . We reply within one business day, Monday through Friday, US Pacific time.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
This solution helps in processing textual data to identify named entities present in the corpus of text.
This solution helps in extracting legal names of organizations and their aliases from text documents.
This is a Named Entity Recognition model built upon a Transformer model from Hugging Face
This solution helps in extracting parent and subsidiary organization relations from text documents.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.