Triple
T4046344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proton rocket |
E84074
|
entity |
| Predicate | typicalPayload |
P45549
|
FINISHED |
| Object | large communications satellites |
—
|
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: large communications satellites | Statement: [Proton rocket, typicalPayload, large communications satellites]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalPayload Context triple: [Proton rocket, typicalPayload, large communications satellites]
-
A.
payloadType
Indicates the kind or category of payload associated with or carried by an entity or action.
-
B.
plannedPayload
Indicates that an entity is designated or scheduled to be carried, delivered, or transported as part of a planned operation or mission.
-
C.
secondaryPayload
Indicates that an entity serves as an additional or subordinate payload associated with a primary payload in an action or relationship.
-
D.
communicationsPayload
Indicates that an entity carries or contains equipment, data, or components specifically intended for communication purposes.
-
E.
compatiblePayload
chosen
Indicates that one entity can be safely or effectively used as the payload of another entity without conflict or required modification.
- 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_69aed930bd5c819083e7dcc14fc44f69 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb6135b481909d2be890a2140ff9 |
completed | March 9, 2026, 4:54 p.m. |
| PD | Predicate disambiguation | batch_69aef900386481909d04555a9ec9b0e3 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:37 p.m.