Triple
T18204894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | mBART |
E435877
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | mBART-50 |
—
|
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: mBART-50 | Statement: [mBART, hasVariant, mBART-50]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: mBART-50 Context triple: [mBART, hasVariant, mBART-50]
-
A.
mBART
chosen
mBART is a multilingual sequence-to-sequence Transformer model designed for tasks like machine translation and text generation across many languages.
-
B.
BART-base
BART-base is a smaller, 12-layer variant of Facebook AI’s BART sequence-to-sequence transformer model, commonly used for tasks like text generation, summarization, and translation.
-
C.
LM-5B
LM-5B is a heavy-lift variant of China’s Long March 5 rocket family, primarily used to launch large modules for the Tiangong space station into low Earth orbit.
-
D.
DeBERTa
DeBERTa is a transformer-based language model developed by Microsoft that improves upon BERT and RoBERTa using disentangled attention and enhanced mask decoder mechanisms for superior natural language understanding.
-
E.
Megatron-LM
Megatron-LM is a large-scale language model training framework developed by NVIDIA, designed to efficiently train massive transformer models through model, tensor, and pipeline parallelism.
- 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.