Triple
T26212018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union of Bukovina with Romania |
E655513
|
entity |
| Predicate | regionNowDividedBetween |
P6497
|
FINISHED |
| Object | Romania |
—
|
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: Romania | Statement: [Union of Bukovina with Romania, regionNowDividedBetween, Romania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionNowDividedBetween Context triple: [Union of Bukovina with Romania, regionNowDividedBetween, Romania]
-
A.
capitalDivision
Indicates that one administrative division serves as the capital of another administrative division or political entity.
-
B.
regionDivision
Indicates a hierarchical or organizational subdivision relationship where one region is partitioned into smaller constituent regions.
-
C.
wasDividedBetween
Indicates that something was partitioned into portions that were allocated to two or more distinct recipients or groups.
-
D.
dividedBetween
chosen
Indicates that something is partitioned or shared among two or more distinct entities or groups.
-
E.
modernCountryDivisionBetween
Indicates a relationship where a modern country’s territory is divided or shared between two or more entities or regions.
- 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_69ee5b49adb4819086545280d4ef6337 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 26, 2026, 8:52 p.m.