Triple
T9298135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tensor Cores |
E223691
|
entity |
| Predicate | presentInArchitecture |
P6684
|
FINISHED |
| Object | Ampere |
E754911
|
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: Ampere | Statement: [Tensor Cores, presentInArchitecture, Ampere]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ampere Context triple: [Tensor Cores, presentInArchitecture, Ampere]
-
A.
Ampere
chosen
Ampere is NVIDIA's GPU microarchitecture known for its improved ray tracing, AI acceleration, and power efficiency across gaming and professional graphics cards.
-
B.
Amper
The Amper is a river in Bavaria, Germany, known for flowing from the Ammersee toward the Isar and ultimately contributing to the Danube river system.
-
C.
Ampère (unit of electric current)
The ampere is the International System of Units (SI) base unit that quantifies electric current.
-
D.
ampere
The ampere is the SI base unit of electric current, defining the amount of electric charge passing a point in a circuit per unit time.
-
E.
André-Marie Ampère
André-Marie Ampère was a pioneering French physicist and mathematician whose work in electromagnetism led to the naming of the unit of electric current, the ampere, in his honor.
- 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_69ca8423edb08190bc0c91287a484768 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd089e3ae88190aa4181cdd85a67b8 |
completed | April 1, 2026, 11:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0b251c4148190a94fafdc23a601d6 |
completed | April 4, 2026, 6:40 a.m. |
Created at: March 30, 2026, 7:36 p.m.