Triple
T3834149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VSS Unity |
E91086
|
entity |
| Predicate | microgravityDuration |
P52281
|
FINISHED |
| Object | a few minutes of microgravity per flight |
—
|
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: a few minutes of microgravity per flight | Statement: [VSS Unity, microgravityDuration, a few minutes of microgravity per flight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: microgravityDuration Context triple: [VSS Unity, microgravityDuration, a few minutes of microgravity per flight]
-
A.
timeInSpace
Indicates the amount of time an entity has spent in outer space.
-
B.
missionDuration
Indicates the length of time over which a mission or operation takes place from start to finish.
-
C.
missionDurationPlanned
Indicates the length of time that a mission is scheduled or intended to last according to its plan.
-
D.
missionDurationType
Indicates the classification of a mission’s length or time span (e.g., short-term, long-term, extended).
-
E.
missionDurationCapability
Indicates the length of time an entity is capable of sustaining or performing a mission or operation.
- 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_69aed960b538819096561c8ed448dec9 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeeb8a27688190866bc41441e2260c |
completed | March 9, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69aee74c2e04819094b94b3c0bac1806 |
completed | March 9, 2026, 3:29 p.m. |
| PDg | Predicate description generation | batch_69aeeb828fb08190901d51edbe8bd304 |
completed | March 9, 2026, 3:47 p.m. |
Created at: March 9, 2026, 3:17 p.m.