Triple

T22489360
Position Surface form Disambiguated ID Type / Status
Subject Clipboard API E555972 entity
Predicate method P859 FINISHED
Object ClipboardItem NE NERFINISHED

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: ClipboardItem | Statement: [Clipboard API, method, ClipboardItem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ClipboardItem
Context triple: [Clipboard API, method, ClipboardItem]
  • A. ClipboardItem chosen
    ClipboardItem is a JavaScript interface representing individual clipboard entries, typically used to read from and write data to the system clipboard via the Clipboard API.
  • B. Clipboard API
    The Clipboard API is a modern web platform interface that allows websites to programmatically read from and write to the system clipboard in a secure, permission-controlled way.
  • C. Clipboard
    The Clipboard is a system feature that temporarily stores data such as text or images so they can be copied and pasted between applications.
  • D. Universal Clipboard
    Universal Clipboard is an Apple ecosystem feature that lets users copy content on one Apple device and paste it seamlessly onto another nearby device using the same iCloud account.
  • E. Clipboard Manager
    Clipboard Manager is an Android system service that lets apps store, retrieve, and manage text and other data on the global clipboard for copy-and-paste operations.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e53897c819088863779f8c50bb0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15c3f3b4c819092bfe6495c61db46 completed April 29, 2026, 1:17 a.m.
Created at: April 16, 2026, 8:49 p.m.