Triple
T9808377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terrain Mapping Camera 2 |
E238207
|
entity |
| Predicate | platformOrbitAltitude |
P12741
|
FINISHED |
| Object | approximately 100 km above lunar surface |
—
|
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: approximately 100 km above lunar surface | Statement: [Terrain Mapping Camera 2, platformOrbitAltitude, approximately 100 km above lunar surface]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: platformOrbitAltitude Context triple: [Terrain Mapping Camera 2, platformOrbitAltitude, approximately 100 km above lunar surface]
-
A.
orbitAltitude
chosen
Indicates the height of an object's orbit above a reference body, typically measured from the body's surface or mean radius.
-
B.
locatedInOrbitAbove
Indicates that one entity is positioned in an orbital path around and above another entity.
-
C.
locatedAtAltitude
Indicates that an entity exists or is positioned at a specific height above a reference level, typically sea level.
-
D.
orbitType
Indicates the specific kind or classification of an object's orbit in relation to the body it revolves around.
-
E.
orbitalPosition
Indicates the relative location or path of one object in its orbit with respect to a central body or reference frame.
- 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_69ca84defac48190abc1148804f184c1 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb21ef32c8190ab4b09d157798451 |
completed | April 2, 2026, 12:02 a.m. |
| PD | Predicate disambiguation | batch_69cd03dd2da881909052fbf29736a773 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:29 p.m.