Triple

T11429318
Position Surface form Disambiguated ID Type / Status
Subject W3C Web Application technologies E270837 entity
Predicate includesStandard P19701 FINISHED
Object Selection API E856226 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: Selection API | Statement: [W3C Web Application technologies, includesStandard, Selection API]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Selection API
Context triple: [W3C Web Application technologies, includesStandard, Selection API]
  • A. Selection API chosen
    The Selection API is a web standard that lets scripts inspect and manipulate the text or content currently selected by the user in a document.
  • B. MatSelect
    MatSelect is an Angular Material UI component that provides a styled, accessible dropdown selection control for Angular applications.
  • C. Selectee List
    The Selectee List is a U.S. government watchlist of air travelers who are subject to enhanced security screening before being allowed to board commercial flights.
  • D. XSELECT
    XSELECT is a software tool used by astronomers to interactively select, filter, and analyze high-energy astrophysics data from various space-based observatories.
  • E. SelectObject
    SelectObject is a Windows GDI function used to select a graphics object, such as a pen, brush, or bitmap, into a device context for subsequent drawing operations.
  • 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_69d6aadeef688190874bcecd88b3dd9b completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d806c1bfb881909720c74fe0fa837f completed April 9, 2026, 8:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5b8d923688190bb4d61d57768e10e completed April 20, 2026, 5:25 a.m.
Created at: April 8, 2026, 9:35 p.m.