Triple
T1000489
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neptune |
E21590
|
entity |
| Predicate | flybyDate_Voyager2 |
P12572
|
FINISHED |
| Object | 1989-08-25 |
—
|
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: 1989-08-25 | Statement: [Neptune, flybyDate_Voyager2, 1989-08-25]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flybyDate_Voyager2 Context triple: [Neptune, flybyDate_Voyager2, 1989-08-25]
-
A.
NeptuneFlybyDate
chosen
Indicates the date on which a spacecraft performs or performed a flyby of Neptune.
-
B.
firstFlybyYear
Indicates the calendar year in which an object or mission first performed a flyby of a specified target.
-
C.
UranusFlybyDate
Indicates the date on which a spacecraft performed a flyby of Uranus.
-
D.
firstSuccessfulFlybyBy
Indicates that the subject is the first spacecraft or mission to successfully perform a flyby of the object specified by the predicate’s value.
-
E.
firstFlybyBy
Indicates that one entity was the spacecraft, probe, or mission that performed the first flyby of another entity (such as a celestial body or target).
- 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_69a493c476b48190b41fc5e793171cc6 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4fb18b88190ae2d620aaaff4f90 |
completed | March 1, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69a4b2b057c48190b9e42df9246b3757 |
completed | March 1, 2026, 9:42 p.m. |
Created at: March 1, 2026, 7:41 p.m.