Triple
T878849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grob G 120 |
E18980
|
entity |
| Predicate | variantOf |
P4680
|
FINISHED |
| Object | Grob G 120TP |
E18980
|
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: Grob G 120TP | Statement: [Grob G 120, variantOf, Grob G 120TP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grob G 120TP Context triple: [Grob G 120, variantOf, Grob G 120TP]
-
A.
Grob G 120
chosen
The Grob G 120 is a German-built, two-seat training aircraft widely used by military air forces for basic flight instruction.
-
B.
Fieseler
Fieseler was a German aircraft manufacturer best known for producing innovative World War II aircraft, including the V-1 flying bomb.
-
C.
Fokker Universal
The Fokker Universal was a rugged, high-wing monoplane of the 1920s widely used for bush flying, cargo transport, and pioneering commercial aviation in remote regions.
-
D.
Junkers Ju 86
The Junkers Ju 86 was a German twin‑engine aircraft of the 1930s used primarily as a medium bomber and later adapted for high‑altitude reconnaissance during World War II.
-
E.
Junkers Ju 52 aircraft
The Junkers Ju 52 was a German tri-motor transport and bomber aircraft widely used in the 1930s and World War II for troop transport, paratroop drops, and cargo missions.
- 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_69a4938db1f081909bcd1ad2713b6096 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4acb1dc20819095b9bb093158b60d |
completed | March 1, 2026, 9:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7c726e6808190b2000051d72b434e |
completed | March 4, 2026, 5:46 a.m. |
Created at: March 1, 2026, 7:39 p.m.