Triple
T18443943
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TY Coronae Australis |
E450605
|
entity |
| Predicate | hasDustObscurationEvents |
P82946
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [TY Coronae Australis, hasDustObscurationEvents, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDustObscurationEvents Context triple: [TY Coronae Australis, hasDustObscurationEvents, yes]
-
A.
hasDustExtinction
Indicates that an entity exhibits or is subject to attenuation of light due to the presence of intervening dust.
-
B.
hasExtendedDustyRegion
Indicates that an entity possesses a surrounding area or zone characterized by dust that extends outward beyond its immediate vicinity.
-
C.
dustFormationObserved
Indicates that the process of dust formation has been detected or recorded as occurring.
-
D.
hasBeenObservedByOccultation
Indicates that an object or phenomenon has been detected or studied through an occultation event, where it is temporarily obscured by another body.
-
E.
hasDust
chosen
Indicates that one entity possesses, contains, or is covered with dust.
- 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_69d8d381d6388190a9e94e9c658174e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e51c142abc8190b4f6f938acdc413d |
completed | April 19, 2026, 6:16 p.m. |
| PD | Predicate disambiguation | batch_69e469c943a4819094c8fdc5971ad3a7 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:30 a.m.