Triple

T5964461
Position Surface form Disambiguated ID Type / Status
Subject Preact E132717 entity
Predicate ecosystem P964 FINISHED
Object Preact Router
Preact Router is a lightweight routing library designed to handle client-side navigation in Preact single-page applications.
E559067 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: Preact Router | Statement: [Preact, ecosystem, Preact Router]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Preact Router
Context triple: [Preact, ecosystem, Preact Router]
  • A. React Router
    React Router is a popular routing library for React applications that enables declarative, client-side navigation and URL management in single-page apps.
  • B. Preact
    Preact is a lightweight, fast alternative to React that offers a similar component-based API in a much smaller bundle size.
  • C. Vue Router
    Vue Router is the official routing library for Vue.js applications, enabling client-side navigation, nested routes, and dynamic route matching.
  • D. SvelteKit
    SvelteKit is a full-stack application framework for building fast, modern web apps with the Svelte UI library, offering routing, server-side rendering, and deployment tooling.
  • E. elm-reactor
    elm-reactor is a development tool for the Elm language that provides a local web server and live-reloading interface for quickly building and testing Elm applications.
  • 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: Preact Router
Triple: [Preact, ecosystem, Preact Router]
Generated description
Preact Router is a lightweight routing library designed to handle client-side navigation in Preact single-page applications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Preact Router
Target entity description: Preact Router is a lightweight routing library designed to handle client-side navigation in Preact single-page applications.
  • A. React Router
    React Router is a popular routing library for React applications that enables declarative, client-side navigation and URL management in single-page apps.
  • B. Preact
    Preact is a lightweight, fast alternative to React that offers a similar component-based API in a much smaller bundle size.
  • C. Vue Router
    Vue Router is the official routing library for Vue.js applications, enabling client-side navigation, nested routes, and dynamic route matching.
  • D. SvelteKit
    SvelteKit is a full-stack application framework for building fast, modern web apps with the Svelte UI library, offering routing, server-side rendering, and deployment tooling.
  • E. elm-reactor
    elm-reactor is a development tool for the Elm language that provides a local web server and live-reloading interface for quickly building and testing Elm applications.
  • 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_69c0086c2364819091e9fe2f58fa2517 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c03a0240cc81909d7c75c7e6d630f7 completed March 22, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e3f32e8481908a6075684287c412 completed March 23, 2026, 6:55 a.m.
NEDg Description generation batch_69c0ebfa3a9c81908a183f995350366b completed March 23, 2026, 7:30 a.m.
NED2 Entity disambiguation (via description) batch_69c0ec61672c8190b98cead75cac84d5 completed March 23, 2026, 7:31 a.m.
Created at: March 22, 2026, 4:03 p.m.