Triple
T2099601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NH90 |
E37062
|
entity |
| Predicate | tailRotorType |
P24155
|
FINISHED |
| Object | conventional tail rotor |
—
|
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: conventional tail rotor | Statement: [NH90, tailRotorType, conventional tail rotor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tailRotorType Context triple: [NH90, tailRotorType, conventional tail rotor]
-
A.
tailRotorConfiguration
chosen
Indicates the specific arrangement or design setup of a vehicle’s tail rotor relative to its main structure or propulsion system.
-
B.
tailRotorBlades
Indicates the relationship in which an entity functions as the rotor blades located at the tail of a rotorcraft, used for stability and directional control.
-
C.
isHelicopterOf
Indicates that one entity is a helicopter that belongs to, is operated by, or is otherwise associated with another entity.
-
D.
propellerType
Indicates the specific kind or classification of propeller associated with an entity.
-
E.
landingGearType
Indicates the specific kind or configuration of landing gear that an object (typically an aircraft or vehicle) 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_69a8861828948190924aa30c08806b3a |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abbab9f5b88190b8a18056dc592dde |
completed | March 7, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69abb7b6274081909df36cd7a7c6a675 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.