Triple
T10046416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple Silicon MacBook Pro |
E207626
|
entity |
| Predicate | firstModelsReleaseDate |
P21814
|
FINISHED |
| Object | 2020-11 |
—
|
LITERAL 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: 2020-11 | Statement: [Apple Silicon MacBook Pro, firstModelsReleaseDate, 2020-11]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstModelsReleaseDate Context triple: [Apple Silicon MacBook Pro, firstModelsReleaseDate, 2020-11]
-
A.
productionModelDebut
Indicates the event or point in time when a model first enters official production or is publicly released as a production version.
-
B.
firstGenerationReleaseDate
chosen
Indicates the calendar date on which the first generation or initial version of something was officially released.
-
C.
firstImagesReleaseDate
Indicates the date on which the first set of images associated with an entity was initially released.
-
D.
yearModelTDevelopmentBegan
Indicates the calendar year in which the development of model T was initiated.
-
E.
screenDebutYear
Indicates the year in which an entity first appeared on screen (such as in film, television, or other recorded visual media).
- F. None of above.
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_69ca835ad0608190b7c80b292da004f5 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cdcf648f548190a7aa3b1594665831 |
completed | April 2, 2026, 2:07 a.m. |
| PD | Predicate disambiguation | batch_69cd4b8d2280819089de27e57babd1f3 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 8:56 p.m.