Triple
T17537419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tensor G3 |
E427096
|
entity |
| Predicate | supportsFeature |
P203
|
FINISHED |
| Object | Tensor Processing Unit |
—
|
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: Tensor Processing Unit | Statement: [Tensor G3, supportsFeature, Tensor Processing Unit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tensor Processing Unit Context triple: [Tensor G3, supportsFeature, Tensor Processing Unit]
-
A.
Tensor Processing Unit
chosen
A Tensor Processing Unit (TPU) is a specialized AI accelerator chip designed by Google to efficiently perform large-scale machine learning computations, particularly for neural networks.
-
B.
Tensor Cores
Tensor Cores are specialized processing units in NVIDIA GPUs designed to accelerate matrix operations for deep learning and AI workloads.
-
C.
NPU
NPU is a leading Chinese research university in Xi’an renowned for its strengths in aeronautics, astronautics, and marine engineering.
-
D.
NPU
NPU is the commonly used abbreviation for the National Police of Ukraine, the country’s central law enforcement agency responsible for maintaining public order and safety.
-
E.
NPU
An NPU (Neural Processing Unit) is a specialized processor designed to accelerate artificial intelligence and machine learning workloads, particularly neural network computations.
- 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_69d889de677081909b22d2657b1f0292 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4536d03dc81908b8a58f66657c01a |
completed | April 19, 2026, 4 a.m. |
Created at: April 10, 2026, 5:49 a.m.