Triple
T15684014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Савиндан |
E380149
|
entity |
| Predicate | обележава се |
P14941
|
FINISHED |
| Object | 27. јануара по грегоријанском календару |
—
|
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: 27. јануара по грегоријанском календару | Statement: [Савиндан, обележава се, 27. јануара по грегоријанском календару]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: обележава се Context triple: [Савиндан, обележава се, 27. јануара по грегоријанском календару]
-
A.
isNotedOn
Indicates that information about one entity is recorded, mentioned, or annotated on another entity (such as a document, record, or medium).
-
B.
marked
Indicates that one entity has been identified, labeled, or highlighted in some way by another entity.
-
C.
observationNote
Indicates that there is an associated free-text comment or remark providing additional details or context about an observation.
-
D.
marque
Indicates that one entity is the brand or make associated with another entity, such as a product, vehicle, or manufactured item.
-
E.
observance
chosen
Indicates the performance or maintenance of a practice, rule, or custom in accordance with prescribed or expected standards.
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f31b5b881908e46ecd9fc6048ab |
completed | April 16, 2026, 2:53 a.m. |
| PD | Predicate disambiguation | batch_69deda8c856c8190882330114f9a1a5f |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:43 a.m.