Triple
T13187504
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pratt & Whitney Canada PT6T Twin‑Pac |
E313894
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | PT6T‑9B |
E588916
|
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: PT6T‑9B | Statement: [Pratt & Whitney Canada PT6T Twin‑Pac, hasVariant, PT6T‑9B]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PT6T‑9B Context triple: [Pratt & Whitney Canada PT6T Twin‑Pac, hasVariant, PT6T‑9B]
-
A.
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.
-
B.
PaLM 2
PaLM 2 is a large-scale language model developed by Google, known for powering various AI features across Google products before being succeeded by the Gemini family of models.
-
C.
PT6
chosen
PT6 is a widely used family of turboprop and turboshaft aircraft engines developed by Pratt & Whitney Canada, renowned for their reliability and versatility in civil and military aviation.
-
D.
GPT-Neo
GPT-Neo is an open-source family of autoregressive language models developed by EleutherAI as a free alternative to OpenAI’s GPT-3.
-
E.
Tianshou
Tianshou is a reinforcement learning library for PyTorch that provides modular, efficient tools and algorithms for training and evaluating RL agents.
- 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_69d806ae1e08819090d95bfe1538cc17 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c4d60688190b34e65bbb5d4c152 |
completed | April 10, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a2e415481908ad1036376f702dc |
completed | May 3, 2026, 8:41 a.m. |
Created at: April 9, 2026, 9:15 p.m.