Triple
T5355251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MOXIE |
E102673
|
entity |
| Predicate | atmosphericFeedstock |
P36779
|
FINISHED |
| Object | Martian carbon dioxide–rich atmosphere |
—
|
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: Martian carbon dioxide–rich atmosphere | Statement: [MOXIE, atmosphericFeedstock, Martian carbon dioxide–rich atmosphere]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: atmosphericFeedstock Context triple: [MOXIE, atmosphericFeedstock, Martian carbon dioxide–rich atmosphere]
-
A.
hasAtmosphere
Indicates that an astronomical body possesses a surrounding layer of gases held by its gravity.
-
B.
featuresAtmosphericProduction
chosen
Indicates that something includes or involves the creation or use of atmospheric effects or conditions as part of its production.
-
C.
secondaryAtmosphericConstituent
Indicates that an entity has a specified substance as a non-primary (secondary) component of its atmosphere.
-
D.
capturesAtmosphereOf
Indicates that one entity successfully conveys or reflects the overall mood, tone, or ambiance characteristic of another entity.
-
E.
atmosphericStudyType
Indicates the specific kind or category of study being conducted on the atmosphere or atmospheric phenomena.
- 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_69bd43d8f7248190b64c140734b5c9a8 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd862dbb008190aef653acddafd38b |
completed | March 20, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69bd845c6f108190832a8d14b356368a |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:01 p.m.