Triple
T16692273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ulsan plant |
E405622
|
entity |
| Predicate | sellsToMarket |
P5252
|
FINISHED |
| Object | domestic South Korean market |
—
|
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: domestic South Korean market | Statement: [Ulsan plant, sellsToMarket, domestic South Korean market]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sellsToMarket Context triple: [Ulsan plant, sellsToMarket, domestic South Korean market]
-
A.
marketedWith
Indicates that two or more products or services are promoted together as part of the same marketing effort or campaign.
-
B.
marketedFor
Indicates that something is promoted, advertised, or positioned as being intended or suitable for a particular use, audience, or purpose.
-
C.
exportMarket
chosen
Indicates that an entity serves as a destination market to which another entity exports goods or services.
-
D.
marketsAs
Indicates that one entity promotes, advertises, or sells another entity as a product, service, or offering in the marketplace.
-
E.
marketsThrough
Indicates that one entity promotes, sells, or distributes its products or services by using another entity as a marketing or sales channel.
- 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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37eaacb948190954231c9e97a4adf |
completed | April 18, 2026, 12:52 p.m. |
| PD | Predicate disambiguation | batch_69e319bc73908190a0e38bc926b31f10 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:19 a.m.