Skip to main content

Minimalist wrapper around Stanford OpenIE

Project description

Python wrapper for Stanford OpenIE

Open information extraction (open IE) refers to the extraction of structured relation triples from plain text, such that the schema for these relations does not need to be specified in advance. For example, Barack Obama was born in Hawaii would create a triple (Barack Obama; was born in; Hawaii), corresponding to the open domain relation "was born in". CoreNLP is a Java implementation of an open IE system as described in the paper:

More information can be found here :


from openie import StanfordOpenIE

with StanfordOpenIE() as client:
    text = 'Barack Obama was born in Hawaii. Richard Manning wrote this sentence.'
    print('Text: %s.' % text)
    for triple in client.annotate(text):
        print('|-', triple)

    graph_image = 'graph.png'
    client.generate_graphviz_graph(text, graph_image)
    print('Graph generated: %s.' % graph_image)

    with open('corpus/pg6130.txt', 'r', encoding='utf8') as r:
        corpus ='\n', ' ').replace('\r', '')

    triples_corpus = client.annotate(corpus[0:50000])
    print('Corpus: %s [...].' % corpus[0:80])
    print('Found %s triples in the corpus.' % len(triples_corpus))
    for triple in triples_corpus[:3]:
        print('|-', triple)

V1 (deprecated)

The unofficial cross-platform Python wrapper for the state-of-art information extraction library from Stanford University.

NOTE: Windows is not currently supported! Works on UNIX systems like Linux and Mac OS.


First of all, make sure Java 1.8 is installed. Open a terminal and run this command to check:

java -version

If this is not the case and if your OS is Ubuntu, you can install it this way:

sudo add-apt-repository ppa:webupd8team/java
sudo apt-get update
sudo apt-get install oracle-java8-installer

The code can be invoked either programmatically or through the command line. The program can be invoked with the following command. It will display [['Barack Obama', ' was', ' born'], ['Barack Obama', ' was born in', ' Hawaii']]

git clone
cd Stanford-OpenIE-Python
echo "Barack Obama was born in Hawaii." > samples.txt
python -f samples.txt

The output should be something like:

Barack Obama | was | born
Barack Obama | was born in | Hawaii


It's possible that you get an error like that one when using the lib for the first time:

AssertionError: ERROR: Call to stanford_ie exited with a non-zero code status

The error is related to the interaction with Java. To troubleshoot it, I would advise to run the python script with the --verbose argument. Search for line executing command = <whatever command> in the logs and copy paste this <whatever command> in your terminal to see the error.

Large Corpus

Sometimes you just want to run the information extraction tool on something larger than just a couple of sentences. I provide a bash script for that. This example runs the tool on the book: The Iliad by Homer, composed of 1.2M characters and 26K lines.

./ corpus/pg6130.txt corpus/pg6130.txt.out
wc -l corpus/pg6130.txt.out
> 23888

Generate Graph

echo "Barack Obama was born in Hawaii." > samples.txt
python -f samples.txt -g

Will generate a GraphViz DOT graph and its related PNG file in /tmp/openie/

Note: Make sure GraphViz is installed beforehand. Try to run the dot command to see if this is the case. If not, run sudo apt-get install graphviz if you're running on Ubuntu.


You can either open an issue or send me an e-mail to Any contributions are welcomed!

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

stanford-openie-1.0.1.tar.gz (4.3 kB view hashes)

Uploaded source

Built Distribution

stanford_openie-1.0.1-py3-none-any.whl (5.4 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page