Triple

T14422397
Position Surface form Disambiguated ID Type / Status
Subject KHTML E357615 entity
Predicate usedIn P98 FINISHED
Object KHTMLPart E357615 NE FINISHED

How this triple was built (2 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: KHTMLPart | Statement: [KHTML, usedIn, KHTMLPart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KHTMLPart
Context triple: [KHTML, usedIn, KHTMLPart]
  • A. KHTML chosen
    KHTML is an open-source HTML layout engine developed by the KDE project that served as the original foundation for Apple’s WebKit browser engine.
  • B. QtWebKit
    QtWebKit is a port of the WebKit browser engine that integrates it with the Qt application framework for embedding web content in Qt-based applications.
  • C. EdgeHTML
    EdgeHTML is a proprietary web browser engine developed by Microsoft for earlier versions of the Microsoft Edge browser before it transitioned to Chromium.
  • D. WebKit
    WebKit is an open-source web browser engine, originally developed by Apple, that powers the rendering and execution of web content in browsers like Safari.
  • E. WebCore
    WebCore is the layout, rendering, and DOM engine at the heart of the WebKit browser framework, responsible for interpreting and displaying web content.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d82793421c8190861eb0e673b085de completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de91102c3c81908f571a1fff3bdd47 completed April 14, 2026, 7:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5bcb131c8190935d9bacb1afc995 completed May 8, 2026, 3:43 a.m.
Created at: April 10, 2026, 1:18 a.m.