Triple

T18799423
Position Surface form Disambiguated ID Type / Status
Subject Bokeh E459723 entity
Predicate component P35 FINISHED
Object Bokeh server
Bokeh server is the backend component of the Bokeh visualization library that enables building and serving interactive, real-time web-based data applications in Python.
E1342438 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Bokeh server | Statement: [Bokeh, component, Bokeh server]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bokeh server
Context triple: [Bokeh, component, Bokeh server]
  • A. Jupyter Server
    Jupyter Server is the backend application that manages and serves Jupyter notebooks, kernels, and related services for frontends like JupyterLab.
  • B. JupyterHub
    JupyterHub is an open-source platform that enables multiple users to access and run Jupyter notebook environments on shared infrastructure, typically for education, research, and collaborative computing.
  • C. JupyterLab
    JupyterLab is a web-based interactive development environment for working with Jupyter notebooks, code, and data.
  • D. Jupyter
    Jupyter is an open-source project that provides interactive computing tools, most notably Jupyter Notebooks, for data science, scientific computing, and education across multiple programming languages.
  • E. JupyterLite
    JupyterLite is a lightweight, browser-based distribution of Jupyter that runs entirely in the web using WebAssembly and in-browser storage, enabling notebooks without a traditional server or local installation.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Bokeh server
Triple: [Bokeh, component, Bokeh server]
Generated description
Bokeh server is the backend component of the Bokeh visualization library that enables building and serving interactive, real-time web-based data applications in Python.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bokeh server
Target entity description: Bokeh server is the backend component of the Bokeh visualization library that enables building and serving interactive, real-time web-based data applications in Python.
  • A. Jupyter Server
    Jupyter Server is the backend application that manages and serves Jupyter notebooks, kernels, and related services for frontends like JupyterLab.
  • B. JupyterHub
    JupyterHub is an open-source platform that enables multiple users to access and run Jupyter notebook environments on shared infrastructure, typically for education, research, and collaborative computing.
  • C. JupyterLab
    JupyterLab is a web-based interactive development environment for working with Jupyter notebooks, code, and data.
  • D. Jupyter
    Jupyter is an open-source project that provides interactive computing tools, most notably Jupyter Notebooks, for data science, scientific computing, and education across multiple programming languages.
  • E. JupyterLite
    JupyterLite is a lightweight, browser-based distribution of Jupyter that runs entirely in the web using WebAssembly and in-browser storage, enabling notebooks without a traditional server or local installation.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8d398c7d4819091cb2f7e48948aeb completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5a02273b481909bc250144a0ace32 completed April 20, 2026, 3:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a054723def4819097961a04087a54a3 completed May 14, 2026, 3:53 a.m.
NEDg Description generation batch_6a0549358ba081909eb649898d1b3a8a completed May 14, 2026, 4:01 a.m.
NED2 Entity disambiguation (via description) batch_6a0549c825f481909d2da63688b36186 completed May 14, 2026, 4:04 a.m.
Created at: April 10, 2026, 11:53 a.m.