Triple
T1329379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PZL-130 Orlik |
E28605
|
entity |
| Predicate | aircraftStructure |
P25338
|
FINISHED |
| Object | all-metal construction |
—
|
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: all-metal construction | Statement: [PZL-130 Orlik, aircraftStructure, all-metal construction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aircraftStructure Context triple: [PZL-130 Orlik, aircraftStructure, all-metal construction]
-
A.
airframeConstruction
chosen
Indicates the method or structural approach used to build an aircraft’s main body and supporting framework.
-
B.
airframe
Indicates that an entity is the structural framework or body of an aircraft associated with another entity (such as a specific model, component, or system).
-
C.
airframeDerivedFrom
Indicates that one airframe design is derived or developed from another pre-existing airframe design.
-
D.
aircraft
Indicates that an entity is an aircraft or functions in the role of an aircraft in the described context.
-
E.
fuselageType
Indicates the specific structural or design category of an aircraft’s fuselage that an entity belongs to or uses.
- 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_69a498561a508190a3e1bc137c2b866a |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c1c30c948190afc6342b3dcda948 |
completed | March 1, 2026, 10:46 p.m. |
| PD | Predicate disambiguation | batch_69a4beef6a188190996f8775bdda8f6c |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:55 p.m.