Triple
T36489419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NASNet |
E899014
|
entity |
| Predicate | top5AccuracyOnImageNetApprox |
P185592
|
FINISHED |
| Object | 96.2% |
—
|
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: 96.2% | Statement: [NASNet, top5AccuracyOnImageNetApprox, 96.2%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: top5AccuracyOnImageNetApprox Context triple: [NASNet, top5AccuracyOnImageNetApprox, 96.2%]
-
A.
improvementOverStateOfTheArtTop5Error
Indicates that something achieves a lower top-5 error rate than the previous state-of-the-art, representing an improvement in performance.
-
B.
top5ErrorRate
Indicates the proportion of instances where the correct answer is not among the top five predicted results.
-
C.
inceptionApproximation
Indicates an approximate or estimated starting point or origin of something, rather than an exact inception time.
-
D.
pretrainedOn
Indicates that a model has been trained in advance using a specified dataset or data source before being applied to downstream tasks.
-
E.
depthApprox
Indicates an approximate or estimated depth relationship between entities, rather than an exact measured depth.
- F. None of above. chosen
Provenance (4 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_69f76e5ad4588190bdbce60c52fbb785 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bccf05bc8190b61fdb2b2a315811 |
completed | May 3, 2026, 9:23 p.m. |
| PDg | Predicate description generation | batch_69f7be9b9ab481908328e0e8d8ac73d4 |
completed | May 3, 2026, 9:31 p.m. |
Created at: May 3, 2026, 4:10 p.m.