Triple
T26062830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Миджур |
E657311
|
entity |
| Predicate | попадаВ |
P96712
|
FINISHED |
| Object | Натура 2000 зони (от българска страна) |
—
|
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: Натура 2000 зони (от българска страна) | Statement: [Миджур, попадаВ, Натура 2000 зони (от българска страна)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: попадаВ Context triple: [Миджур, попадаВ, Натура 2000 зони (от българска страна)]
-
A.
находитсяК
chosen
Indicates that one entity is located at, in, or near another entity.
-
B.
имаПриступСа
Indicates that one entity can be accessed or reached from another entity via a specified side, direction, or approach.
-
C.
посада
Indicates that one entity holds a specific official position, role, or office in relation to another entity (such as an organization or institution).
-
D.
pakad
Indicates the act of catching, holding, or seizing someone or something, typically by grasping or capturing it.
-
E.
расположенаНа
Indicates that one entity is located on the surface or area of another entity.
- 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_69ee5bbd788481909e22bd7153d0c037 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f606941410819098a15b288273c3e1 |
completed | May 2, 2026, 2:13 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 7:20 p.m.