Triple
T849046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GPT-3.5 |
E18340
|
entity |
| Predicate | inferenceMode |
P5072
|
FINISHED |
| Object | autoregressive token sampling |
—
|
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: autoregressive token sampling | Statement: [GPT-3.5, inferenceMode, autoregressive token sampling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inferenceMode Context triple: [GPT-3.5, inferenceMode, autoregressive token sampling]
-
A.
usedOnMode
Indicates that something is applied, operated, or functions specifically in a given mode or operational setting.
-
B.
mode
chosen
Indicates the manner, method, or way in which an action, process, or interaction is carried out or occurs.
-
C.
inductionType
Indicates the specific method or process by which something is brought into a state, condition, or role (e.g., how an entity is initiated, introduced, or caused to occur).
-
D.
approximationType
Indicates the specific method or scheme used to approximate a value, function, or relationship in a given context.
-
E.
neuralEngineType
Indicates the specific kind or category of neural processing engine associated with or used by an entity.
- 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_69a4938b04208190b82e1df6b572c548 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac1fac3481909cba7070ce31a9b3 |
completed | March 1, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69a4aa807adc8190ad808a573cf8e923 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:38 p.m.