Triple
T19433661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | iOS 15 |
E486179
|
entity |
| Predicate | feature |
P374
|
FINISHED |
| Object | Live Text |
—
|
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: Live Text | Statement: [iOS 15, feature, Live Text]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Live Text Context triple: [iOS 15, feature, Live Text]
-
A.
Live Text
chosen
Live Text is a macOS and iOS feature that uses on-device intelligence to recognize and interact with text in photos, screenshots, and live camera views.
-
B.
ARD Text
ARD Text is the teletext service of the German public broadcaster ARD, providing news, information, and program details via television text pages.
-
C.
Living Videotext
Living Videotext was an early software company best known for developing pioneering outliner and scripting tools for personal computers in the 1980s.
-
D.
TXT
TXT is the stock ticker symbol for Textron Inc., a U.S.-based industrial conglomerate known for its aerospace, defense, and specialized vehicle businesses.
-
E.
Office Lens
Office Lens is a Microsoft mobile scanning app that captures documents, whiteboards, and other content with a device camera and converts them into editable, shareable digital files.
- 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_69d8e8d7ad488190a3373045029b0f3b |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6335dae10819096e1825741f814ed |
completed | April 20, 2026, 2:08 p.m. |
Created at: April 10, 2026, 1:37 p.m.