Triple
T18205220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HuBERT |
E435884
|
entity |
| Predicate | publishedAt |
P30105
|
FINISHED |
| Object | Interspeech 2021 |
—
|
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: Interspeech 2021 | Statement: [HuBERT, publishedAt, Interspeech 2021]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Interspeech 2021 Context triple: [HuBERT, publishedAt, Interspeech 2021]
-
A.
INTERSPEECH
chosen
INTERSPEECH is a leading international conference focused on speech communication and technology, covering research in speech processing, recognition, synthesis, and related fields.
-
B.
ISCA
ISCA (International Symposium on Computer Architecture) is a premier annual academic conference focused on research in computer architecture and related areas.
-
C.
IEEE Transactions on Audio, Speech, and Language Processing
IEEE Transactions on Audio, Speech, and Language Processing is a leading peer-reviewed journal covering research and advances in audio, speech, and natural language signal processing.
-
D.
Speech Analysis, Synthesis and Perception
"Speech Analysis, Synthesis and Perception" is a foundational technical book that systematically explores the theory, modeling, and processing of human speech signals for analysis, synthesis, and recognition.
-
E.
IEEE International Conference on Acoustics, Speech, and Signal Processing
The IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) is a leading annual scientific conference that showcases cutting-edge research and advances in signal processing, including audio, speech, image, and multimedia technologies.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e222831081908f7d5500424e3acb |
completed | April 19, 2026, 2:09 p.m. |
Created at: April 10, 2026, 10:32 a.m.