Triple
T29971861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vostok 2 |
E761337
|
entity |
| Predicate | spaceFirst |
P176329
|
FINISHED |
| Object | first person to sleep in space |
—
|
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: first person to sleep in space | Statement: [Vostok 2, spaceFirst, first person to sleep in space]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spaceFirst Context triple: [Vostok 2, spaceFirst, first person to sleep in space]
-
A.
pace
Indicates the rate or speed at which an action, process, or sequence progresses over time.
-
B.
spaceLine
Indicates a relationship where entities are connected or arranged along a line within a spatial context or coordinate system.
-
C.
usesSpace
Indicates that one entity occupies, consumes, or makes use of physical or conceptual space associated with another entity.
-
D.
plaintextSpace
Indicates a relationship where text is represented or transmitted in an unencrypted, human-readable form with spaces preserved as literal characters.
-
E.
spaceflownWith
Indicates that two entities have traveled together in space on the same spaceflight or mission.
- F. None of above. chosen
Provenance (4 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_69f22467626081908d5afea489590e96 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f6dfcafd0c81908d86662948c539d6 |
completed | May 3, 2026, 5:40 a.m. |
| PD | Predicate disambiguation | batch_69f6de07836481908785cde9c511920b |
completed | May 3, 2026, 5:32 a.m. |
| PDg | Predicate description generation | batch_69f6df418f488190a5e7ff41f32dceda |
completed | May 3, 2026, 5:38 a.m. |
Created at: April 29, 2026, 6:32 p.m.