Triple
T4214810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hayabusa |
E94188
|
entity |
| Predicate | sampleReturnCapsule |
P40193
|
FINISHED |
| Object | heat-shielded reentry capsule |
—
|
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: heat-shielded reentry capsule | Statement: [Hayabusa, sampleReturnCapsule, heat-shielded reentry capsule]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sampleReturnCapsule Context triple: [Hayabusa, sampleReturnCapsule, heat-shielded reentry capsule]
-
A.
capsule
chosen
Indicates that one entity is a capsule containing, enclosing, or encapsulating another entity.
-
B.
numberOfCapsules
Indicates the quantity or count of capsules associated with an entity or event.
-
C.
returnCapability
Indicates the ability or provision for something to be sent, given, or transferred back to its original sender, owner, or source.
-
D.
isTimeCapsule
Indicates that something functions as a time capsule, preserving items or information to be opened or accessed at a later, specified time.
-
E.
wasReturnedIn
Indicates that an item previously taken or sent was brought or sent back to its original source or owner at a specific time or in a specific context.
- 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_69b3451997e08190851db4a9a588837d |
completed | March 12, 2026, 10:58 p.m. |
| NER | Named-entity recognition | batch_69b34e098da881909a0cc339cc186627 |
completed | March 12, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69b347efd9b08190bb50f82e4e7fe06d |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:04 p.m.