Triple
T11000654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PSLV-C20 |
E259993
|
entity |
| Predicate | launchedSatellite |
P32888
|
FINISHED |
| Object | AAUSAT3 |
E898932
|
NE 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: AAUSAT3 | Statement: [PSLV-C20, launchedSatellite, AAUSAT3]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AAUSAT3 Context triple: [PSLV-C20, launchedSatellite, AAUSAT3]
-
A.
AAUSAT3
chosen
AAUSAT3 is a Danish student-built CubeSat developed at Aalborg University for educational purposes and space technology research.
-
B.
ArgoMoon CubeSat
ArgoMoon CubeSat is a small Italian-built spacecraft designed to demonstrate proximity operations and imaging capabilities in deep space during NASA’s Artemis I mission.
-
C.
EQUULEUS CubeSat
EQUULEUS CubeSat is a small Japanese-led spacecraft designed to demonstrate low-energy trajectory techniques and study Earth's plasmasphere from cislunar space.
-
D.
GSAT-30
GSAT-30 is an Indian geostationary communications satellite operated by ISRO to provide television, telecommunications, and broadband services.
-
E.
BioSentinel CubeSat
BioSentinel CubeSat is a NASA bioscience mission designed to study the effects of
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa8a6a548190a750f944ccdc8064 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d796d68b608190a8d016b9383e82f8 |
completed | April 9, 2026, 12:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e37486b23081909ad282397c50a913 |
completed | April 18, 2026, 12:09 p.m. |
Created at: April 8, 2026, 9:25 p.m.