Triple
T5241389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grob Aircraft |
E118348
|
entity |
| Predicate | product |
P490
|
FINISHED |
| Object | Grob G 120 |
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 120 | Statement: [Grob Aircraft, product, Grob G 120]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grob G 120 Context triple: [Grob Aircraft, product, Grob G 120]
-
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.
Junkers G 38
The Junkers G 38 was a large German four-engined transport aircraft of the late 1920s and early 1930s, notable for its distinctive thick wing that housed passenger cabins.
-
C.
Fieseler Fi 156 Storch
The Fieseler Fi 156 Storch was a German World War II liaison and reconnaissance aircraft renowned for its exceptional short takeoff and landing (STOL) capabilities.
-
D.
Dornier Do 31
The Dornier Do 31 was a German experimental vertical take-off and landing (VTOL) jet transport aircraft developed in the 1960s for potential military airlift use.
-
E.
Fairchild-Dornier
Fairchild-Dornier was a German-American aircraft manufacturer formed in the 1990s that focused on regional and business jets before declaring bankruptcy in the early 2000s.
- 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_69bd4467db0881909b3b0982df32cc8f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b2c50508190b84bab216c30cbfe |
completed | March 20, 2026, 4:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69befe65e3048190899a6316dc4c89eb |
completed | March 21, 2026, 8:24 p.m. |
Created at: March 20, 2026, 1:49 p.m.