Triple
T13576319
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Junkers F 13 |
E324293
|
entity |
| Predicate | fuselageSurfaceFeature |
P71007
|
FINISHED |
| Object | corrugated metal skin |
—
|
LITERAL 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: corrugated metal skin | Statement: [Junkers F 13, fuselageSurfaceFeature, corrugated metal skin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fuselageSurfaceFeature Context triple: [Junkers F 13, fuselageSurfaceFeature, corrugated metal skin]
-
A.
fuselageShape
Indicates the geometric form or contour of an object's fuselage, describing how its main body is shaped.
-
B.
fuselageType
Indicates the specific structural or design category of an aircraft’s fuselage that an entity belongs to or uses.
-
C.
fuselageCovering
chosen
Indicates the material or structure that forms the outer covering or skin of an aircraft’s fuselage.
-
D.
fuselageVariant
Indicates that one fuselage is a specific version or variant derived from another fuselage design.
-
E.
fuselagePosition
Indicates the spatial placement or alignment of a fuselage relative to a reference frame or other aircraft components.
- F. None of above.
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_69d80769100c819099111274614f5ed2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb02b1f108190a12af382d1de70bb |
completed | April 12, 2026, 2:46 p.m. |
| PD | Predicate disambiguation | batch_69dbae161a0481909f9d3f40ca4e0ac5 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:48 p.m.