Triple
T1037804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Starliner spacecraft |
E22403
|
entity |
| Predicate | landingSystem |
P14975
|
FINISHED |
| Object | parachutes and airbags |
—
|
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: parachutes and airbags | Statement: [Starliner spacecraft, landingSystem, parachutes and airbags]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: landingSystem Context triple: [Starliner spacecraft, landingSystem, parachutes and airbags]
-
A.
landingMethod
chosen
Indicates the manner or technique by which something or someone arrives and comes to rest at a destination, typically from the air or space.
-
B.
landingArea
Indicates that a location or surface serves as a designated area where something (such as an aircraft, object, or person) can land.
-
C.
landingDistance
Indicates the required or actual distance needed for an aircraft or object to complete a landing from approach to full stop.
-
D.
landingGear
Indicates that an entity’s landing gear is present, deployed, or otherwise involved in a landing-related state or action relative to another entity or context.
-
E.
landingMethodFirstStage
Indicates the method by which the first stage of a launch vehicle returns and lands after separation.
- 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_69a493d91478819094cc01fb65564bc1 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b97c64a88190bf1119fdd4940bf3 |
completed | March 1, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69a4b729f8488190b2042bd9c625a833 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:41 p.m.