Triple
T25750344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stardust |
E648454
|
entity |
| Predicate | sampleReturnCapsuleOperator |
P73375
|
FINISHED |
| Object | NASA Johnson Space Center |
—
|
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: NASA Johnson Space Center | Statement: [Stardust, sampleReturnCapsuleOperator, NASA Johnson Space Center]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sampleReturnCapsuleOperator Context triple: [Stardust, sampleReturnCapsuleOperator, NASA Johnson Space Center]
-
A.
capsuleRecovery
chosen
Indicates the action or process of retrieving a capsule after its use, mission, or deployment.
-
B.
isReusableCapsule
Indicates that a capsule is designed to be used multiple times rather than being discarded after a single use.
-
C.
capsuleSystem
Indicates a relationship where an entity functions as or belongs to a capsule-based system (e.g., a system organized around or implemented via capsules).
-
D.
numberOfCapsules
Indicates the quantity or count of capsules associated with an entity or event.
-
E.
capsuleType
Indicates the specific kind or category of capsule associated with an entity.
- 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_69e7ab314d788190b3abe19e114080e1 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f603bb02288190b40cedbed5b9651d |
completed | May 2, 2026, 2:01 p.m. |
| PD | Predicate disambiguation | batch_69f602d07590819085ac34b189613104 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 22, 2026, 4:34 a.m.