Triple
T18204705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OPT |
E435873
|
entity |
| Predicate | includesVariant |
P455
|
FINISHED |
| Object | OPT-175B |
—
|
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: OPT-175B | Statement: [OPT, includesVariant, OPT-175B]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: OPT-175B Context triple: [OPT, includesVariant, OPT-175B]
-
A.
OPT-175B
chosen
OPT-175B is Meta AI’s largest OPT-series language model, featuring 175 billion parameters for advanced natural language understanding and generation.
-
B.
OPT-350M
OPT-350M is a 350-million-parameter variant of Meta AI's Open Pretrained Transformer language model family, designed as a smaller, efficient model for research and experimentation.
-
C.
OPT-30B
OPT-30B is a 30-billion-parameter large language model in Meta AI's OPT family, designed as an open, research-focused alternative to proprietary transformer-based models.
-
D.
Opti
Opti is a friendly, futuristic robot character that served as one of the official mascots of Expo 2020 Dubai.
-
E.
OK-150
OK-150 is a Soviet-era marine nuclear reactor design used to power early nuclear icebreakers such as the Lenin.
- 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.