Triple
T32508323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shenzhou 11 |
E830859
|
entity |
| Predicate | crewLaunchMassCategory |
P108887
|
FINISHED |
| Object | medium crewed spacecraft mission |
—
|
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: medium crewed spacecraft mission | Statement: [Shenzhou 11, crewLaunchMassCategory, medium crewed spacecraft mission]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crewLaunchMassCategory Context triple: [Shenzhou 11, crewLaunchMassCategory, medium crewed spacecraft mission]
-
A.
launchVehicleType
Indicates the type or category of launch vehicle used to carry a payload or mission into space.
-
B.
coreLaunchVehicle
Indicates that one entity serves as the primary launch vehicle used to propel another entity (such as a payload or mission) into space.
-
C.
spacecraftSizeClass
chosen
Indicates the size category or class to which a spacecraft belongs based on its overall dimensions or mass.
-
D.
primaryLaunchVehicleType
Indicates the type or category of launch vehicle that is primarily used to carry a payload into space.
-
E.
primaryLaunchVehicleForCargo
Indicates that a launch vehicle is the main rocket used to carry a specific cargo into space.
- 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_69f3492318348190ba37fb6b5f1d67f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c44d21648190ada905d52e251b1f |
completed | May 3, 2026, 3:43 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2a14b081908162923dfbf0a6f4 |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 1 a.m.