Triple

T7934358
Position Surface form Disambiguated ID Type / Status
Subject Keynote E184252 entity
Predicate partOf P40 FINISHED
Object iWork E35338 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: iWork | Statement: [Keynote, partOf, iWork]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: iWork
Context triple: [Keynote, partOf, iWork]
  • A. Apple iWork chosen
    Apple iWork is Apple's suite of productivity applications, including Pages, Numbers, and Keynote, designed for document creation, spreadsheets, and presentations across macOS, iOS, and iCloud.
  • B. iLife
    iLife was a suite of multimedia and creativity applications developed by Apple for macOS, including tools for photo management, video editing, music creation, and website building.
  • C. iWeb
    iWeb was a discontinued Apple application for creating and publishing personal websites and blogs with drag-and-drop ease as part of the iLife suite.
  • D. MacWrite
    MacWrite was one of the first WYSIWYG word processors for the original Macintosh, showcasing the platform’s graphical user interface and desktop publishing capabilities.
  • E. Quattro Pro
    Quattro Pro is a spreadsheet software program, originally developed by Borland and later owned by Corel, known for competing with Lotus 1-2-3 and Microsoft Excel.
  • 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_69ca8290c21c8190906a5ca6fe2b03c4 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3aeb132c8190bea4906aaf51b869 completed March 31, 2026, 3:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc564a4fac8190972f9dfa7c026ea8 completed March 31, 2026, 11:18 p.m.
Created at: March 30, 2026, 5:08 p.m.