Triple
T36514844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PSLV-C2 |
E900007
|
entity |
| Predicate | commercialCustomers |
P77553
|
FINISHED |
| Object | Republic of Korea |
—
|
NE NERFINISHED |
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: Republic of Korea | Statement: [PSLV-C2, commercialCustomers, Republic of Korea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commercialCustomers Context triple: [PSLV-C2, commercialCustomers, Republic of Korea]
-
A.
commercialCustomer
chosen
Indicates a relationship where an entity purchases or uses goods or services from another entity for commercial or business purposes.
-
B.
commercialSingle
Indicates that an entity is a commercially released single (a standalone commercial music or audio release).
-
C.
commercialForm
Indicates the commercial or marketed form in which something (such as a product, substance, or medicine) is offered or sold.
-
D.
commercialAccess
Indicates that an entity is permitted to use or access something for commercial or profit-generating purposes.
-
E.
commercialCategory
Indicates the type of commercial classification or business category under which an entity or transaction is grouped.
- 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_69f76e5dada881909da2d34bc7a9202a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fb2e940d5c8190bceae77daf4ef512 |
completed | May 6, 2026, 12:05 p.m. |
| PD | Predicate disambiguation | batch_69f9fec70bd881909c658a3c5020318b |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:10 p.m.