Triple
T1979685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arabsat-6A |
E42995
|
entity |
| Predicate | spacecraftBusVariant |
P12569
|
FINISHED |
| Object | A2100-based platform |
—
|
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: A2100-based platform | Statement: [Arabsat-6A, spacecraftBusVariant, A2100-based platform]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spacecraftBusVariant Context triple: [Arabsat-6A, spacecraftBusVariant, A2100-based platform]
-
A.
spacecraftBus
chosen
Indicates that one entity serves as the primary structural and support platform (bus) for a spacecraft, integrating and housing its subsystems.
-
B.
spacecraftShape
Indicates the geometric form or physical configuration that a spacecraft possesses.
-
C.
spacecraft
Indicates that an entity is a vehicle or object designed to travel or operate in outer space.
-
D.
orbiterDesignation
Indicates that one entity is designated as an orbiter (spacecraft or object in orbit) associated with another entity.
-
E.
notableOrbiter
Indicates that one entity is a particularly significant or well-known artificial satellite or spacecraft that orbits another entity.
- 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_69a88713ddc88190a969715658ebe7a8 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb96f932881908bebfc4176fda7c0 |
completed | March 7, 2026, 5:36 a.m. |
| PD | Predicate disambiguation | batch_69abb798d288819083132cf14605bd02 |
completed | March 7, 2026, 5:28 a.m. |
Created at: March 4, 2026, 7:36 p.m.