Triple
T8741989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RD-107 |
E207525
|
entity |
| Predicate | successor |
P78
|
FINISHED |
| Object | RD-107A |
E207525
|
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: RD-107A | Statement: [RD-107, successor, RD-107A]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RD-107A Context triple: [RD-107, successor, RD-107A]
-
A.
RD-107
chosen
RD-107 is a Soviet-designed liquid-fueled rocket engine, best known for powering the first stages of early R-7 family launch vehicles used in historic missions like Sputnik and Vostok.
-
B.
RD-181
RD-181 is a Russian-built liquid-fueled rocket engine used to power the first stage of certain orbital launch vehicles, notably Northrop Grumman’s Antares.
-
C.
RD-180
The RD-180 is a Russian-built, two-chamber liquid-fueled rocket engine that has powered several American launch vehicles, notably variants of the Atlas V.
-
D.
RD-93
RD-93 is a Russian turbofan jet engine derived from the Klimov RD-33, optimized to power lightweight fighter aircraft such as the Pakistani-Chinese JF-17 Thunder.
-
E.
BE-7 engine
The BE-7 engine is Blue Origin’s high-performance liquid hydrogen–liquid oxygen rocket engine designed primarily to power lunar landers such as the company’s Blue Moon vehicle.
- 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_69ca835a03a081909d4d4cd01a18c9fb |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5d6fd5dc8190906b7147f27c5d46 |
completed | March 31, 2026, 11:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf42f282e48190ad158063e265e0f0 |
completed | April 3, 2026, 4:32 a.m. |
Created at: March 30, 2026, 6:38 p.m.