Triple
T23579165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korea |
E582150
|
entity |
| Predicate | dividedAlongLine |
P21958
|
FINISHED |
| Object | 38th parallel north |
—
|
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: 38th parallel north | Statement: [Korea, dividedAlongLine, 38th parallel north]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dividedAlongLine Context triple: [Korea, dividedAlongLine, 38th parallel north]
-
A.
divisionLine
chosen
Indicates a boundary or separating line that divides one area, group, or portion from another.
-
B.
dividedIn
Indicates that one entity is partitioned or separated into multiple distinct parts, sections, or groups represented by another entity.
-
C.
dividedBetween
Indicates that something is partitioned or shared among two or more distinct entities or groups.
-
D.
isDividedFrom
Indicates that one entity is separated or partitioned from another, typically by a boundary, barrier, or dividing line.
-
E.
dividedBy
Indicates that one quantity is separated into a specified number of equal parts or groups by another quantity, representing a division relationship between them.
- 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_69e248f8d8248190acd5aee77f0d1709 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1afd7dbe88190b05ff03f952bf7c3 |
completed | April 29, 2026, 7:14 a.m. |
| PD | Predicate disambiguation | batch_69f118bcc0b08190b25a8dddfd461a0e |
completed | April 28, 2026, 8:29 p.m. |
Created at: April 17, 2026, 6:39 p.m.