Triple
T23479592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boeing 737-900ER |
E570366
|
entity |
| Predicate | wingletsOption |
P151660
|
FINISHED |
| Object | Split Scimitar Winglets |
—
|
NE NERFINISHED |
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: Split Scimitar Winglets | Statement: [Boeing 737-900ER, wingletsOption, Split Scimitar Winglets]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Split Scimitar Winglets Context triple: [Boeing 737-900ER, wingletsOption, Split Scimitar Winglets]
-
A.
Whitcomb winglet
chosen
The Whitcomb winglet is an aerodynamic wingtip device designed to reduce drag and improve fuel efficiency on aircraft, pioneered by NASA engineer Richard T. Whitcomb.
-
B.
Ramport Aero
Ramport Aero is the company responsible for managing and operating Zhukovsky International Airport near Moscow, Russia.
-
C.
Wing
Wing is an experimental mobile operating system and user interface project developed by X (formerly Google X) to explore new paradigms in smartphone interaction and design.
-
D.
Wing
Wing is a Japanese lingerie and intimate apparel brand known for its comfortable, everyday undergarments for women.
-
E.
Wing
Wing is a record label imprint associated with the release of the song "Feels Good."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245af8a88819084f2704f6d265a92 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a74f48d8819080e875aaea8b46b3 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:02 p.m.