Triple
T17765200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IR2 camera |
E443484
|
entity |
| Predicate | onboardSince |
P64490
|
FINISHED |
| Object | Akatsuki launch |
—
|
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: Akatsuki launch | Statement: [IR2 camera, onboardSince, Akatsuki launch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onboardSince Context triple: [IR2 camera, onboardSince, Akatsuki launch]
-
A.
onboardSinceLaunch
chosen
Indicates that an entity has been continuously involved or participating in something from its initial launch date onward.
-
B.
onBoard
Indicates that one entity is physically located on or within a vehicle, vessel, or platform operated or used by another entity.
-
C.
usedWhenOnBoard
Indicates that something is employed or utilized while a person or object is on board a vehicle, vessel, or similar conveyance.
-
D.
hasOnboardFeature
Indicates that an entity includes or is equipped with a particular feature as part of its built-in or onboard capabilities.
-
E.
onboardPlatform
Indicates that an entity is being added, integrated, or enrolled onto a particular platform so it can start operating or participating there.
- 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_69d8b9edf16c8190a59ebd245d378f4f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e485fb2a3c81908887d1d36aee942d |
completed | April 19, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69e3d8d8e538819084f1584426b41d5e |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:11 a.m.