Triple
T11078751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OV-102 Columbia |
E261932
|
entity |
| Predicate | totalOrbitsCompleted |
P8796
|
FINISHED |
| Object | over 4,800 |
—
|
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: over 4,800 | Statement: [OV-102 Columbia, totalOrbitsCompleted, over 4,800]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: totalOrbitsCompleted Context triple: [OV-102 Columbia, totalOrbitsCompleted, over 4,800]
-
A.
orbitsCovered
Indicates that one entity completes or spans a specified number of orbital revolutions around another entity.
-
B.
totalOrbits
chosen
Indicates the total number of orbital paths or revolutions one entity completes around another within a defined system or timeframe.
-
C.
orbitsCompletedAroundMars
Indicates the number of full orbital revolutions an object has completed around Mars.
-
D.
orbitsServed
Indicates that a mission, vehicle, or service has operated for or provided coverage during a specified number of orbital revolutions around a celestial body.
-
E.
numberOfOrbitalPlanes
Indicates the specific count of distinct orbital planes associated with an object or system.
- 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_69d6aa9983c08190b0ef61603b69feac |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d799953d58819096b645a1377e70f2 |
completed | April 9, 2026, 12:20 p.m. |
| PD | Predicate disambiguation | batch_69d74415403c81909778bcd829e8832e |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.