Triple
T9002939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WWDC 2016 |
E215077
|
entity |
| Predicate | keynoteSpeaker |
P33706
|
FINISHED |
| Object | Eddy Cue |
E427879
|
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: Eddy Cue | Statement: [WWDC 2016, keynoteSpeaker, Eddy Cue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eddy Cue Context triple: [WWDC 2016, keynoteSpeaker, Eddy Cue]
-
A.
Eddy Cue
chosen
Eddy Cue is a senior Apple executive best known for overseeing the company’s internet software and services, including iTunes, the App Store, and iCloud.
-
B.
Mark Hurd (former)
Mark Hurd was an American technology executive best known for serving as CEO of Hewlett-Packard and later as co-CEO of Oracle Corporation.
-
C.
Phil Schiller
Phil Schiller is a longtime Apple executive who has played a key role in the company’s product marketing and major keynote presentations.
-
D.
Greg Zeschuk
Greg Zeschuk is a Canadian video game developer and physician best known as a co-founder of the acclaimed role-playing game studio BioWare.
-
E.
Frank Lanning
Frank Lanning was an American character actor of the silent film era, known for his supporting roles in numerous Westerns and early Hollywood productions.
- 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_69ca83a12d648190b1e4fe11e8a31890 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6957bd5481908ce74f32f8d197de |
completed | April 1, 2026, 12:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfd0e0a28c81909b6d2c6cd80e24d4 |
completed | April 3, 2026, 2:38 p.m. |
Created at: March 30, 2026, 7:05 p.m.