Interpret prediction results from text entity extraction models
Stay organized with collections
Save and categorize content based on your preferences.
After requesting a prediction, Vertex AI returns results based on your
model's objective. Predictions from entity extraction models return annotations
for each document, such as the location of detected entities, the assigned
labels, and confidence scores.
The confidence communicates how confident your model accurately identified and
labeled each entity. The higher the number, the higher the model's confidence in
the correctness of the prediction.
Example batch prediction output
The following sample is the predicted result for an entity extraction model that
was trained to detect diseases. The offsets (start and end character offsets)
specify the location where the model detected an entity in the document, and the
content field shows the detected entity.
The display names show the labels that the model associated with each entity,
such as SpecificDisease or DiseaseClass. The labels map to the text segments
in order.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[],[],null,["# Interpret prediction results from text entity extraction models\n\n| Starting on September 15, 2024, you can only customize classification, entity extraction, and sentiment analysis objectives by moving to Vertex AI Gemini prompts and tuning. Training or updating models for Vertex AI AutoML for Text classification, entity extraction, and sentiment analysis objectives will no longer be available. You can continue using existing Vertex AI AutoML Text models until June 15, 2025. For a comparison of AutoML text and Gemini, see [Gemini for AutoML text users](/vertex-ai/docs/start/automl-gemini-comparison). For more information about how Gemini offers enhanced user experience through improved prompting capabilities, see [Introduction to tuning](/vertex-ai/generative-ai/docs/models/tune-gemini-overview). To get started with tuning, see [Model tuning for Gemini text models](/vertex-ai/generative-ai/docs/models/tune_gemini/tune-gemini-learn)\n\nAfter requesting a prediction, Vertex AI returns results based on your\nmodel's objective. Predictions from entity extraction models return annotations\nfor each document, such as the location of detected entities, the assigned\nlabels, and confidence scores.\n\nThe confidence communicates how confident your model accurately identified and\nlabeled each entity. The higher the number, the higher the model's confidence in\nthe correctness of the prediction.\n\nExample batch prediction output\n-------------------------------\n\nThe following sample is the predicted result for an entity extraction model that\nwas trained to detect diseases. The offsets (start and end character offsets)\nspecify the location where the model detected an entity in the document, and the\n`content` field shows the detected entity.\n\nThe display names show the labels that the model associated with each entity,\nsuch as `SpecificDisease` or `DiseaseClass`. The labels map to the text segments\nin order.\n\n\n| **Note**: The following JSON Lines example includes line breaks for\n| readability. In your JSON Lines files, line breaks are included only after each\n| each JSON object.\n\n\u003cbr /\u003e\n\n\n```\n{\n \"key\": 1,\n \"predictions\": {\n \"ids\": [\n \"1234567890123456789\",\n \"2234567890123456789\",\n \"3234567890123456789\"\n ],\n \"displayNames\": [\n \"SpecificDisease\",\n \"DiseaseClass\",\n \"SpecificDisease\"\n ],\n \"textSegmentStartOffsets\": [13, 40, 57],\n \"textSegmentEndOffsets\": [29, 51, 75],\n \"confidences\": [\n 0.99959725141525269,\n 0.99912621492484128,\n 0.99935531616210938\n ]\n }\n}\n```"]]