Triple
T5497900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Smart Keyboard |
E144255
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | Apple |
E3002
|
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: Apple | Statement: [Smart Keyboard, brand, Apple]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Apple Context triple: [Smart Keyboard, brand, Apple]
-
A.
Apple
Apple is a widely cultivated fruit known for its crisp texture, sweet-tart flavor, and central role in cuisines and agricultural traditions around the world.
-
B.
Apple Inc.
chosen
Apple Inc. is a multinational technology company best known for designing and selling consumer electronics like the iPhone, Mac, and iPad, along with software and digital services.
-
C.
Apple One
Apple One is Apple’s subscription bundle that combines multiple services like iCloud storage, music, video, fitness, and news into a single monthly plan.
-
D.
Apple Market
Apple Market is a historic covered market in London’s Covent Garden, known for its stalls selling crafts, antiques, and artisan goods to locals and tourists.
-
E.
Apple hardware
Apple hardware refers to the physical computing devices and electronic products designed and manufactured by Apple Inc., including computers, smartphones, tablets, wearables, and accessories.
- 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_69c008f5a2748190bce7a39aabf87a6d |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01b8f28448190bfd58c36798d7b75 |
completed | March 22, 2026, 4:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c059c555148190925b2f678979b418 |
completed | March 22, 2026, 9:06 p.m. |
Created at: March 22, 2026, 3:32 p.m.