Triple
T27524019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japan–South Korea |
E694786
|
entity |
| Predicate | seaBetween |
P49633
|
FINISHED |
| Object | Sea of Japan |
—
|
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: Sea of Japan | Statement: [Japan–South Korea, seaBetween, Sea of Japan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seaBetween Context triple: [Japan–South Korea, seaBetween, Sea of Japan]
-
A.
seaOf
Indicates a relationship where one entity is metaphorically or literally surrounded or filled by another like a vast sea, emphasizing overwhelming abundance or expansiveness.
-
B.
seaType
Indicates the specific classification or category of a sea associated with an entity.
-
C.
seaConnection
chosen
Indicates a relationship where two places are connected or accessible to each other via the sea, such as by maritime routes or coastal adjacency.
-
D.
seaRepresents
Indicates that one entity serves as a symbolic, visual, or conceptual representation of another within a maritime or sea-related context.
-
E.
separatesSea
Indicates that an agent causes a sea or large body of water to divide into distinct parts or sections.
- 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_69ef538550208190aa9de8e2cb260d93 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62f2e2df88190948551f6fd67a65a |
completed | May 2, 2026, 5:06 p.m. |
| PD | Predicate disambiguation | batch_69f623ac3a9c8190a6ee0c137b09e4b0 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 1:22 p.m.