Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
JevNER is a Python SDK for zero-shot multilingual named entity recognition. It turns a System One judgment model into an NER pipeline that returns nested entity forests with calibrated probabilities, supporting custom JSON taxonomies and 24 languages.
How it uses Jev
JevNER uses Jev (and other System One models) to answer Noul/Choice questions about entity detection and typing on text windows. The model returns calibrated probabilities, which the SDK assembles into a nested entity forest with offsets and multi-type rankings.
Primitives:choicenoul
Technique worth stealing
Using calibrated probabilities from a judgment model to build a nested entity forest from source-text offsets.
Try it
pip install -U jevner, then call JevNER()(text) with TYPESAFE_API_KEY set.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.70
- Shows a System One patternnot found in the excerpt0.09
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.37 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 4 Nov 2026.