Triple
T13349861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earth's atmosphere |
E318041
|
entity |
| Predicate | hasAverageCompositionByVolume |
P109132
|
FINISHED |
| Object | about 78% nitrogen |
—
|
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: about 78% nitrogen | Statement: [Earth's atmosphere, hasAverageCompositionByVolume, about 78% nitrogen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAverageCompositionByVolume Context triple: [Earth's atmosphere, hasAverageCompositionByVolume, about 78% nitrogen]
-
A.
hasMassFraction
Indicates that a specified portion of a substance’s total mass is attributable to a particular component or constituent.
-
B.
hasMeanDensity
Indicates that one entity possesses a specified average mass per unit volume (mean density).
-
C.
isTypicallyFilledWith
Indicates that one entity is commonly or usually occupied, loaded, or contained by another entity.
-
D.
hasSurfaceComposition
Indicates that one entity has a surface made up of, or characterized by, the material or composition specified by another entity.
-
E.
hasMainAtmosphericComponent
Indicates that one entity has another entity as the primary constituent of its atmosphere.
- 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_69d806b5a3c08190b42c267fb092f98a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99e8c2f1c819094f0970f35f18afa |
completed | April 11, 2026, 1:06 a.m. |
| PD | Predicate disambiguation | batch_69d98f6e53d88190bd6aa42f69b10ffb |
completed | April 11, 2026, 12:01 a.m. |
| PDg | Predicate description generation | batch_69d99073e4708190843bda3a1ae78f43 |
completed | April 11, 2026, 12:06 a.m. |
Created at: April 9, 2026, 9:31 p.m.