Triple
T11856156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RADARSAT program |
E282043
|
entity |
| Predicate | usesSatelliteType |
P96316
|
FINISHED |
| Object | radar imaging satellite |
—
|
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: radar imaging satellite | Statement: [RADARSAT program, usesSatelliteType, radar imaging satellite]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesSatelliteType Context triple: [RADARSAT program, usesSatelliteType, radar imaging satellite]
-
A.
satelliteType
chosen
Indicates that one entity is classified as a specific type or category of satellite relative to another entity.
-
B.
typeOfSatelliteOperated
Indicates that one entity operates or manages a satellite of a specified type or category in relation to another entity.
-
C.
hasSatelliteStatus
Indicates that one entity holds the status of being a satellite (e.g., dependent, subordinate, or orbiting body) in relation to another entity.
-
D.
hasSatelliteTerminal
Indicates that an entity is equipped with or connected to a satellite communication terminal.
-
E.
hasSatelliteLocation
Indicates that an entity has a secondary or remote location associated with it, such as a branch, satellite office, or auxiliary site.
- 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_69d6ab287ba48190a5178779fd19b9b7 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a697f4108190af984932d2118472 |
completed | April 10, 2026, 7:28 a.m. |
| PD | Predicate disambiguation | batch_69d8a2573dbc8190ab432e8e28fde6cc |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:43 p.m.