Triple
T805254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | API for Whisper |
E17415
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | OpenAI Whisper model |
E17415
|
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: OpenAI Whisper model | Statement: [API for Whisper, relatedTo, OpenAI Whisper model]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: OpenAI Whisper model Context triple: [API for Whisper, relatedTo, OpenAI Whisper model]
-
A.
API for Whisper
chosen
API for Whisper is OpenAI’s cloud-based interface for programmatically accessing its Whisper speech recognition model to transcribe and translate audio.
-
B.
Versoix
Versoix is a Swiss municipality on the shores of Lake Geneva, known as a residential suburb of Geneva with lakeside promenades and a mix of urban and natural landscapes.
-
C.
WaveNet
WaveNet is a deep generative neural network architecture for raw audio that produces highly natural-sounding speech and other audio signals.
-
D.
GPT-3.5
GPT-3.5 is a large language model that generates human-like text and powers conversational AI applications such as advanced chatbots and coding assistants.
-
E.
GPT-3
GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
- 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_69a4937ae8a08190b5084a03d532b30e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4aabff3d88190bec4299fa0d87df0 |
completed | March 1, 2026, 9:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a68926c04081908923a7d114d1842d |
completed | March 3, 2026, 7:09 a.m. |
Created at: March 1, 2026, 7:38 p.m.