Triple
T3492770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Defense Support Program |
E73775
|
entity |
| Predicate | orbitalRegime |
P17317
|
FINISHED |
| Object | geosynchronous orbit |
—
|
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: geosynchronous orbit | Statement: [Defense Support Program, orbitalRegime, geosynchronous orbit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orbitalRegime Context triple: [Defense Support Program, orbitalRegime, geosynchronous orbit]
-
A.
orbitType
Indicates the specific kind or classification of an object's orbit in relation to the body it revolves around.
-
B.
hasOrbitalRegion
chosen
Indicates that one entity occupies, lies within, or is associated with a specific orbital zone or region around another body.
-
C.
onOrbitalRoute
Indicates that one object is currently traveling along or positioned on a defined orbital path around another body.
-
D.
orbitsBeyond
Indicates that one celestial body orbits at a greater average distance from a central object than another specified body.
-
E.
orbits
Indicates that one object moves in a curved, usually repetitive path around another object due to a central force such as gravity.
- 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_69ad85cca8d4819088494e9f3340fab5 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbbabd1708190b1ca4cbc87462b5b |
completed | March 8, 2026, 6:10 p.m. |
| PD | Predicate disambiguation | batch_69adae0b34908190b2bb5766a2231f7a |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:18 p.m.