Triple
T5259599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proteus (moon) |
E118790
|
entity |
| Predicate | rankBySizeAroundNeptune |
P62570
|
FINISHED |
| Object | second largest moon of Neptune |
—
|
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: second largest moon of Neptune | Statement: [Proteus (moon), rankBySizeAroundNeptune, second largest moon of Neptune]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankBySizeAroundNeptune Context triple: [Proteus (moon), rankBySizeAroundNeptune, second largest moon of Neptune]
-
A.
distanceFromNeptune
Indicates the measured or calculated spatial separation between a given entity and the planet Neptune.
-
B.
relativeSizeToPluto
Indicates how the size of one entity compares to the size of Pluto.
-
C.
rankByDistanceFromSun
Indicates an ordering of entities based on how close or far they are from the Sun, with position determined by distance.
-
D.
relativeSizeToEarth
Indicates the comparative size of an entity when measured relative to the size of Earth.
-
E.
areLargestMoonsOf
Indicates that the referenced moons are the largest natural satellites belonging to the specified celestial bodies.
- F. None of above. chosen
Provenance (4 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_69bd446a42c88190b7ecbef006561d55 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7bcced6881909bdb7ac5471a37fe |
completed | March 20, 2026, 4:54 p.m. |
| PD | Predicate disambiguation | batch_69bd77c55224819096c0bcfcfae79bd3 |
completed | March 20, 2026, 4:37 p.m. |
| PDg | Predicate description generation | batch_69bd7bcabe58819096255672664513b1 |
completed | March 20, 2026, 4:54 p.m. |
Created at: March 20, 2026, 1:50 p.m.