# \#ner **URL:** https://support.prodi.gy/tag/ner/6.md [Latest](https://support.prodi.gy/latest.md) · [Categories](https://support.prodi.gy/categories.md) · [Tags](https://support.prodi.gy/tags.md) --- ## [Annotation Flowchart: Named Entity Recognition](https://support.prodi.gy/t/annotation-flowchart-named-entity-recognition/1556)
**Author:** [@ines](https://support.prodi.gy/u/ines)\ **Replies:** 26\ **Last updated:** [January 23, 2024, 2:33pm UTC](https://support.prodi.gy/t/annotation-flowchart-named-entity-recognition/1556 "2024-01-23T14:33:06Z")
Just shared this on Twitter – if you find flowcharts like this useful, I'm happy to make more :smiley: Updated on October 18, 2022: New versions of the NER flowcharts! See our Twitter thread for more details. --- ## [training on MACOS M2 GPU](https://support.prodi.gy/t/training-on-macos-m2-gpu/7680)
**Author:** [@angelo](https://support.prodi.gy/u/angelo)\ **Replies:** 6\ **Last updated:** [June 18, 2026, 8:19am UTC](https://support.prodi.gy/t/training-on-macos-m2-gpu/7680 "2026-06-18T08:19:44Z")
hi there i have a some label dataset with 23.000 samples on 3 labels, and is taking forever to train my model (more than 1h) and train-curve take almost 4h, is using just a single core in my MACOS M2 GPU. Is it possibl… --- ## [Guidance Needed on Using LLMs with Prodigy for Spanish Coreference Annotation](https://support.prodi.gy/t/guidance-needed-on-using-llms-with-prodigy-for-spanish-coreference-annotation/7666)
**Author:** [@angelo](https://support.prodi.gy/u/angelo)\ **Replies:** 1\ **Last updated:** [May 14, 2026, 2:40pm UTC](https://support.prodi.gy/t/guidance-needed-on-using-llms-with-prodigy-for-spanish-coreference-annotation/7666 "2026-05-14T14:40:30Z")
Hello, I hope you are doing well. I am currently trying to train a spaCy model to resolve coreferences with good accuracy in Spanish. My main challenge is that I need to annotate thousands of text entries, and I am no… --- ## [Custom Logger Function in spaCy v3.8.14](https://support.prodi.gy/t/custom-logger-function-in-spacy-v3-8-14/7664)
**Author:** [@dave-espinosa](https://support.prodi.gy/u/dave-espinosa)\ **Replies:** 2\ **Last updated:** [May 7, 2026, 9:38pm UTC](https://support.prodi.gy/t/custom-logger-function-in-spacy-v3-8-14/7664 "2026-05-07T21:38:00Z")
Hello, I am updating a custom NER model, from v3.6.1 to v3.8.14 (current one at present day). I am reusing some samples originally labeled with Prodigy. To do so, I am using a previously built GCP Pipeline (former Vert… --- ## [load data from parquet and display metadata in ner.manual UI](https://support.prodi.gy/t/load-data-from-parquet-and-display-metadata-in-ner-manual-ui/7663)
**Author:** [@nikita](https://support.prodi.gy/u/nikita)\ **Replies:** 2\ **Last updated:** [April 22, 2026, 12:24pm UTC](https://support.prodi.gy/t/load-data-from-parquet-and-display-metadata-in-ner-manual-ui/7663 "2026-04-22T12:24:35Z")
dear explosion team, I have a parquet file with a couple of columns which I want to use as input for ther ner.manual recipe. I managed to get it to work with a little trial and error (the parquet loader isn't documented… --- ## [No metadata when using \`ner.silver-to-gold\` recipe](https://support.prodi.gy/t/no-metadata-when-using-ner-silver-to-gold-recipe/7633)
**Author:** [@it176131](https://support.prodi.gy/u/it176131)\ **Replies:** 4\ **Last updated:** [November 5, 2025, 7:49pm UTC](https://support.prodi.gy/t/no-metadata-when-using-ner-silver-to-gold-recipe/7633 "2025-11-05T19:49:39Z")
I’m using the ner.silver-to-gold recipe to combine my binary annotations produced via the ner.teach recipe. When I view the UI I notice that the original metadata is not there. Upon further inspection, it looks like the "… --- ## [Question about configuration file when use en\_core\_scibert model for ner](https://support.prodi.gy/t/question-about-configuration-file-when-use-en-core-scibert-model-for-ner/7583)
**Author:** [@Fangjian](https://support.prodi.gy/u/Fangjian)\ **Replies:** 7\ **Last updated:** [September 1, 2025, 10:21am UTC](https://support.prodi.gy/t/question-about-configuration-file-when-use-en-core-scibert-model-for-ner/7583 "2025-09-01T10:21:36Z")
Dear Prodigy team: I'm training a custom NER model using the en\_core\_sci\_scibert base model to identify a new entity label not included in the original model. I have already annotated my training data using ner.manual, … --- ## [Query regarding ner.manual input field for OCR-corrected data (Prodigy pdf.ocr.correct)](https://support.prodi.gy/t/query-regarding-ner-manual-input-field-for-ocr-corrected-data-prodigy-pdf-ocr-correct/7597)
**Author:** [@dh\_gerard](https://support.prodi.gy/u/dh_gerard)\ **Replies:** 1\ **Last updated:** [August 12, 2025, 8:01am UTC](https://support.prodi.gy/t/query-regarding-ner-manual-input-field-for-ocr-corrected-data-prodigy-pdf-ocr-correct/7597 "2025-08-12T08:01:01Z")
Dear Prodigy Support Team, I am currently working on a digital humanities project involving historical letter collections, using Prodigy for my NLP pipeline. I've successfully completed the OCR correction phase using pd… --- ## [\`db-merge\` concatenates rather than merges](https://support.prodi.gy/t/db-merge-concatenates-rather-than-merges/7585)
**Author:** [@jhandsel](https://support.prodi.gy/u/jhandsel)\ **Replies:** 3\ **Last updated:** [July 8, 2025, 8:29am UTC](https://support.prodi.gy/t/db-merge-concatenates-rather-than-merges/7585 "2025-07-08T08:29:38Z")
I’m training a NER model with several entity types. I tagged each entity type as a separate task, so I now have several versions of my dataset, each annotated with a different entity type. I want to merge the datasets s… --- ## [ERROR: Can't fetch tasks. Make sure the server is running correctly when running ner.correct](https://support.prodi.gy/t/error-cant-fetch-tasks-make-sure-the-server-is-running-correctly-when-running-ner-correct/7584)
**Author:** [@Fangjian](https://support.prodi.gy/u/Fangjian)\ **Replies:** 1\ **Last updated:** [July 1, 2025, 8:44am UTC](https://support.prodi.gy/t/error-cant-fetch-tasks-make-sure-the-server-is-running-correctly-when-running-ner-correct/7584 "2025-07-01T08:44:36Z")
Dear prodigy team: I created an annotated dataset for NER using the ner.manual command with the SciBERT model. When I tried to use ner.correct to review all my previous annotations, it started smoothly without any error… --- ## [Merging or finding the best annotation from multi annotator](https://support.prodi.gy/t/merging-or-finding-the-best-annotation-from-multi-annotator/7572)
**Author:** [@sigitpurnomo](https://support.prodi.gy/u/sigitpurnomo)\ **Replies:** 4\ **Last updated:** [June 13, 2025, 3:37pm UTC](https://support.prodi.gy/t/merging-or-finding-the-best-annotation-from-multi-annotator/7572 "2025-06-13T15:37:39Z")
Hi all, I have performed NER annotation using task routing with the feedoverlap: true configuration. The annotation process involves 6 annotators. How do I get only the best dataset to use in training the model? Is it p… --- ## [Which base\_model to use for ner.manual](https://support.prodi.gy/t/which-base-model-to-use-for-ner-manual/7547)
**Author:** [@Fangjian](https://support.prodi.gy/u/Fangjian)\ **Replies:** 2\ **Last updated:** [April 28, 2025, 2:58pm UTC](https://support.prodi.gy/t/which-base-model-to-use-for-ner-manual/7547 "2025-04-28T14:58:58Z")
Hi, I have a simple workflow question hoping you could help me to clarify. I have decided to use scispaCy's en\_core\_sci\_scibert to train my NER model with a custom entity in heavy scientific papers. My understanding is… --- ## [Is it possible to have a recipe receive multiple streams?](https://support.prodi.gy/t/is-it-possible-to-have-a-recipe-receive-multiple-streams/7535)
**Author:** [@SanVijey](https://support.prodi.gy/u/SanVijey)\ **Replies:** 1\ **Last updated:** [April 8, 2025, 4:53pm UTC](https://support.prodi.gy/t/is-it-possible-to-have-a-recipe-receive-multiple-streams/7535 "2025-04-08T16:53:33Z")
We are currently creating a relations recipe, which consists of two blocks. We want the relations block to only consist of the numerical tokens/spans of the text (as those tokens are what we are creating relationships be… --- ## [Multi-Task Training with ProdigyHF](https://support.prodi.gy/t/multi-task-training-with-prodigyhf/7530)
**Author:** [@samirmsallem](https://support.prodi.gy/u/samirmsallem)\ **Replies:** 1\ **Last updated:** [March 24, 2025, 12:07pm UTC](https://support.prodi.gy/t/multi-task-training-with-prodigyhf/7530 "2025-03-24T12:07:52Z")
Hi there, I am quite new to using Prodigy. I have Recently came across custom recipes and created a recipe to annotate a dataset with NER labels and text classification at the same time. My goal is to fine tune a huggi… --- ## [Misalignment for tokenization when use ner.llm.fetch and bert.ner.manual](https://support.prodi.gy/t/misalignment-for-tokenization-when-use-ner-llm-fetch-and-bert-ner-manual/7518)
**Author:** [@Fangjian](https://support.prodi.gy/u/Fangjian)\ **Replies:** 8\ **Last updated:** [March 12, 2025, 5:26pm UTC](https://support.prodi.gy/t/misalignment-for-tokenization-when-use-ner-llm-fetch-and-bert-ner-manual/7518 "2025-03-12T17:26:14Z")
I'm using ner.llm.fetch to generate pre-annotated NER examples, which I then refine using bert.ner.manual with --tokenizer-vocab ./cased\_vocab.txt parameter. However, the annotations from ner.llm.fetch become misaligned … --- ## [Is there any way to annotate text with HTML tags in it ?](https://support.prodi.gy/t/is-there-any-way-to-annotate-text-with-html-tags-in-it/7509)
**Author:** [@dhavalv83](https://support.prodi.gy/u/dhavalv83)\ **Replies:** 1\ **Last updated:** [February 25, 2025, 8:53am UTC](https://support.prodi.gy/t/is-there-any-way-to-annotate-text-with-html-tags-in-it/7509 "2025-02-25T08:53:49Z")
Hello, We have texts with multiple different HTML tags in it. We want to annotate the texts in such a way that HTML tags not shown in UI, but their indexes count in tokens and spans. The text should also be seen in well… --- ## [Merging datasets of same input data to combine separately annotated entities](https://support.prodi.gy/t/merging-datasets-of-same-input-data-to-combine-separately-annotated-entities/7506)
**Author:** [@DGMS90](https://support.prodi.gy/u/DGMS90)\ **Replies:** 2\ **Last updated:** [February 17, 2025, 8:58am UTC](https://support.prodi.gy/t/merging-datasets-of-same-input-data-to-combine-separately-annotated-entities/7506 "2025-02-17T08:58:54Z")
Hi, I've annotated two identical datasets containing 5,000 texts. I annotated a different non-overlapping entity type on each respective iteration of the 5,000 texts. I'm now wanting to merge the datasets to have a com… --- ## [All labels highlighted although only one label specified](https://support.prodi.gy/t/all-labels-highlighted-although-only-one-label-specified/7498)
**Author:** [@tushar](https://support.prodi.gy/u/tushar)\ **Replies:** 3\ **Last updated:** [February 6, 2025, 11:43am UTC](https://support.prodi.gy/t/all-labels-highlighted-although-only-one-label-specified/7498 "2025-02-06T11:43:39Z")
Hi, To speed up the annotation and training, I took my data (data.jsonl) and annotated it (with 8 labels) using llm and then used it to correct and verify the data. The approach I follow is to annotate / correct one lab… --- ## [Training few new entities: Result very low](https://support.prodi.gy/t/training-few-new-entities-result-very-low/7481)
**Author:** [@tushar](https://support.prodi.gy/u/tushar)\ **Replies:** 3\ **Last updated:** [January 29, 2025, 12:50pm UTC](https://support.prodi.gy/t/training-few-new-entities-result-very-low/7481 "2025-01-29T12:50:48Z")
Hi All, I am pretty new to Prodigy, AI and LLM. Tring again after a few years now. I am trying to train and build a domain specific model (recruitment). I have annotated about 20K records, trained them but the accuracy… --- ## [Training a new model, using OpenAI API](https://support.prodi.gy/t/training-a-new-model-using-openai-api/7482)
**Author:** [@tushar](https://support.prodi.gy/u/tushar)\ **Replies:** 2\ **Last updated:** [January 18, 2025, 2:09am UTC](https://support.prodi.gy/t/training-a-new-model-using-openai-api/7482 "2025-01-18T02:09:38Z")
Hi, I plan to train a new model on top of an existing model en\_core\_web\_lg for 13 odd entities. I'll do that one by one. However, I was wondering if there is any out of the box support for OpenAI API to be used which c… --- ## [Resolving UserWarning: \[W036\] The component 'entity\_ruler' does not have any patterns defined](https://support.prodi.gy/t/resolving-userwarning-w036-the-component-entity-ruler-does-not-have-any-patterns-defined/7484)
**Author:** [@AmirNickkar](https://support.prodi.gy/u/AmirNickkar)\ **Replies:** 1\ **Last updated:** [January 16, 2025, 11:01am UTC](https://support.prodi.gy/t/resolving-userwarning-w036-the-component-entity-ruler-does-not-have-any-patterns-defined/7484 "2025-01-16T11:01:57Z")
Greetings, I trained a multi-label NER prodigy model for semantic analysis purposes. It seems the entity ruler isn't reading anything from the prodigy pre-trained model. I am using the command in below to load the prodi… --- ## [Legal Documents - Process to read raw PDF and extract paragraphs into jsonl format](https://support.prodi.gy/t/legal-documents-process-to-read-raw-pdf-and-extract-paragraphs-into-jsonl-format/7463)
**Author:** [@dmnxprss](https://support.prodi.gy/u/dmnxprss)\ **Replies:** 6\ **Last updated:** [January 14, 2025, 2:56pm UTC](https://support.prodi.gy/t/legal-documents-process-to-read-raw-pdf-and-extract-paragraphs-into-jsonl-format/7463 "2025-01-14T14:56:34Z")
Background: I am working with a large amount of legal documents where I want to utilize NER, NER-Relationships, Text Classification, Document Classification to extract information from them. Essentially, I want to do som… --- ## [Data annotation : Query Regarding Data Annotation and Merging in Prodigy](https://support.prodi.gy/t/data-annotation-query-regarding-data-annotation-and-merging-in-prodigy/7480)
**Author:** [@Manoj](https://support.prodi.gy/u/Manoj)\ **Replies:** 1\ **Last updated:** [January 10, 2025, 1:05pm UTC](https://support.prodi.gy/t/data-annotation-query-regarding-data-annotation-and-merging-in-prodigy/7480 "2025-01-10T13:05:47Z")
Hi Team, I am Manoj Goyal. I have a query related to data annotation in Prodigy. I have three datasets named ner\_resume\_person, ner\_resume\_org, and ner\_resume\_course. I want to merge these datasets into one. To do thi… --- ## [Does ner.llm.correct produce overlapping entities?](https://support.prodi.gy/t/does-ner-llm-correct-produce-overlapping-entities/7477)
**Author:** [@DGMS90](https://support.prodi.gy/u/DGMS90)\ **Replies:** 3\ **Last updated:** [January 10, 2025, 12:47pm UTC](https://support.prodi.gy/t/does-ner-llm-correct-produce-overlapping-entities/7477 "2025-01-10T12:47:03Z")
Hey, I'm just looking for some advice on some NER annotations that I'm doing. I'm currently using the ner.llm.correct recpie to connect to a model hosted in Azure (GPT 4o-mini). The task is to annotate job titles, and … --- ## [Data annotation : Error in merge datasets](https://support.prodi.gy/t/data-annotation-error-in-merge-datasets/7476)
**Author:** [@Manoj](https://support.prodi.gy/u/Manoj)\ **Replies:** 5\ **Last updated:** [January 10, 2025, 12:42pm UTC](https://support.prodi.gy/t/data-annotation-error-in-merge-datasets/7476 "2025-01-10T12:42:38Z")
Dear Team, This is Manoj Goyal I am currently working on data annotation using the en\_core\_web\_lg model and have followed the below steps: Annotating with "Person": Created annotations for the Person entity. Genera… --- ## [Prodigy-HF NER with HF SpanMarker model, is it possible?](https://support.prodi.gy/t/prodigy-hf-ner-with-hf-spanmarker-model-is-it-possible/7475)
**Author:** [@Hellyeah](https://support.prodi.gy/u/Hellyeah)\ **Replies:** 1\ **Last updated:** [January 6, 2025, 1:48pm UTC](https://support.prodi.gy/t/prodigy-hf-ner-with-hf-spanmarker-model-is-it-possible/7475 "2025-01-06T13:48:31Z")
Hi, I want to use the following HF model \*\[tomaarsen/span-marker-bert-base-acronyms\]\* to jump start NER on my dataset. This model works perfectly with spaCy's SpanMarker integration, but I can't seem to get it to wor… --- ## [Prediction model using prodigy trained model runs very slow](https://support.prodi.gy/t/prediction-model-using-prodigy-trained-model-runs-very-slow/7455)
**Author:** [@AmirNickkar](https://support.prodi.gy/u/AmirNickkar)\ **Replies:** 5\ **Last updated:** [December 26, 2024, 10:03am UTC](https://support.prodi.gy/t/prediction-model-using-prodigy-trained-model-runs-very-slow/7455 "2024-12-26T10:03:40Z")
I am trying to create a label prediction model that can read the text and extract the trained labels that I prepared in prodigy. To do that I created an annotated dataset in prodigy and created a trained model and used t… --- ## [Text spans and Image spans simultaneously](https://support.prodi.gy/t/text-spans-and-image-spans-simultaneously/3280)
**Author:** [@sanjayss34](https://support.prodi.gy/u/sanjayss34)\ **Replies:** 10\ **Last updated:** [December 20, 2024, 12:39pm UTC](https://support.prodi.gy/t/text-spans-and-image-spans-simultaneously/3280 "2024-12-20T12:39:53Z")
I'm trying to build a tool that will allow me to draw boxes in an image (using "image\_manual") and highlight corresponding portions of a text input (would be similar to NER). However, when I try to use these two views to… --- ## [Use one big NER model or a lot of smaller ones?](https://support.prodi.gy/t/use-one-big-ner-model-or-a-lot-of-smaller-ones/7462)
**Author:** [@toadle](https://support.prodi.gy/u/toadle)\ **Replies:** 3\ **Last updated:** [December 20, 2024, 12:23pm UTC](https://support.prodi.gy/t/use-one-big-ner-model-or-a-lot-of-smaller-ones/7462 "2024-12-20T12:23:42Z")
I have a conceptual question about NER models: Our use case: We are working on categorizing and extracting data from bank turnover purposes. Currently, we can predict one or several categories for a bank turnover using… --- ## [UI bug with colors for ner.manual](https://support.prodi.gy/t/ui-bug-with-colors-for-ner-manual/7448)
**Author:** [@didmar](https://support.prodi.gy/u/didmar)\ **Replies:** 1\ **Last updated:** [December 6, 2024, 9:19am UTC](https://support.prodi.gy/t/ui-bug-with-colors-for-ner-manual/7448 "2024-12-06T09:19:52Z")
:bug: Bug description: When using a custom theme with colors for each label, UI uses the wrong color after a tag is removed. :man\_walking:t4:Reproduction steps: How can we recreate the bug? Create sample.jsonl with … [Next page](https://support.prodi.gy/tag/ner/6.md?match_all_tags=true&page=1&tags%5B%5D=ner)