Triple
T17568611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eddy Cue |
E427879
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Apple Books |
—
|
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: Apple Books | Statement: [Eddy Cue, notableWork, Apple Books]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Apple Books Context triple: [Eddy Cue, notableWork, Apple Books]
-
A.
Apple Books
chosen
Apple Books is Apple’s e-book and audiobook platform and reading app, available across its devices for purchasing, organizing, and enjoying digital books and audio content.
-
B.
Apple Publishing
Apple Publishing is the music publishing arm associated with The Beatles’ Apple Records, handling rights and licensing for the label’s compositions.
-
C.
Google Play Books
Google Play Books is a digital distribution service and e-book/audiobook reader platform from Google that lets users purchase, download, and read or listen to books across devices.
-
D.
Kobo eBookstore
Kobo eBookstore is an online digital bookstore offering a wide catalog of e-books and audiobooks for purchase and download, primarily for use with Kobo e-readers and apps.
-
E.
App Store
The App Store is Apple’s official digital marketplace for discovering, purchasing, and downloading apps and games on iOS, iPadOS, macOS, watchOS, and tvOS devices.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4592f29d08190bc3de905d35af849 |
completed | April 19, 2026, 4:25 a.m. |
Created at: April 10, 2026, 5:50 a.m.