# Add more 3 new entity type

**URL:** <https://support.prodi.gy/t/add-more-3-new-entity-type/2162>\
**Category:** Uncategorized\
**Tags:** usage, ner\
**Created:** [October 31, 2019, 12:09am UTC](https://support.prodi.gy/t/add-more-3-new-entity-type/2162 "2019-10-31T00:09:56Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![desynilaaa](https://avatars.discourse-cdn.com/v4/letter/d/a88e57/32.png) [@desynilaaa](https://support.prodi.gy/u/desynilaaa)\
**Post date:** [October 31, 2019, 12:09am UTC](https://support.prodi.gy/t/add-more-3-new-entity-type/2162/1 "2019-10-31T00:09:56Z")

</div>

Hello, I'm a new user of prodigy.  
I want to ask, if I want to add 4 new labels and still keeping for the old labels in the en\_core\_web\_sm model, how should I do?  
I read from Prodigy Flowchart if I want to add more than 3 new entities, I should using ner.manual then ner.batch-train. I did it. I want to use existing and newly added labels in the same time.  
when I want to test the model that I expect, which model am I calling in spacy? did I make mistake? Sorry for my bad English

---

<div class="post-metadata">

**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\
**Post date:** [October 31, 2019, 11:11am UTC](https://support.prodi.gy/t/add-more-3-new-entity-type/2162/2 "2019-10-31T11:11:05Z")

</div>

Hi! Can you share the `ner.batch-train` command you ran? If you set an `--output` argument on the command line, the model will be saved to that directory. For example:

```bash
prodigy ner.batch-train your_dataset blank:en --output /path/to/model --n-iter 10

```

The above will train from a blank English model using your dataset and it will save the result to `/path/to/model`. In spaCy, you can then do:

```python
nlp = spacy.load("/path/to/model")

```

---

<div class="post-metadata">

**Author:** ![desynilaaa](https://avatars.discourse-cdn.com/v4/letter/d/a88e57/32.png) [@desynilaaa](https://support.prodi.gy/u/desynilaaa)\
**Post date:** [October 31, 2019, 11:31am UTC](https://support.prodi.gy/t/add-more-3-new-entity-type/2162/3 "2019-10-31T11:31:13Z")

</div>

if i want to mix entity in en\_core\_web\_sm and my new entity, what should I do?

---

<div class="post-metadata">

**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\
**Post date:** [October 31, 2019, 6:34pm UTC](https://support.prodi.gy/t/add-more-3-new-entity-type/2162/4 "2019-10-31T18:34:27Z")

</div>

Ah, I thought you had already done the annotation. One thing you can try is using the `ner.make-gold` recipe with the labels you want to keep, plus the new labels. For example:

```bash
prodigy ner.make_gold your_dataset en_core_web_sm your_data.jsonl --label PERSON,ORG,GPE,NEW_LABEL1,NEW_LABEL2

```

The `--label` values set on the command line are the labels you can use. Prodigy will also highlight everything the model already predicts for the labels in the model (for example, `PERSON`). This lets you annotate faster.

---

<div class="post-metadata">

**Author:** ![desynilaaa](https://avatars.discourse-cdn.com/v4/letter/d/a88e57/32.png) [@desynilaaa](https://support.prodi.gy/u/desynilaaa)\
**Post date:** [November 1, 2019, 1:29am UTC](https://support.prodi.gy/t/add-more-3-new-entity-type/2162/5 "2019-11-01T01:29:32Z")

</div>

whoo, I see. Thank you 🙂