Triple
T23009290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crveno-beli |
E572862
|
entity |
| Predicate | cyrillicSpelling |
P34124
|
FINISHED |
| Object | Црвено-бели |
—
|
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: Црвено-бели | Statement: [Crveno-beli, cyrillicSpelling, Црвено-бели]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cyrillicSpelling Context triple: [Crveno-beli, cyrillicSpelling, Црвено-бели]
-
A.
CyrillicName
Indicates that an entity has a name written in the Cyrillic script.
-
B.
hasCyrillicAlphabetForm
chosen
Indicates that an entity has a corresponding representation or form written in the Cyrillic alphabet.
-
C.
usesFixedSpellingsForCommonSyllables
Indicates that an entity consistently applies predetermined, standard spellings for frequently occurring syllables.
-
D.
usesStandardOrthographyOf
Indicates that one entity writes or represents language according to the standard orthographic system defined for another entity.
-
E.
correspondsToEnglishSpelling
Indicates that one representation, form, or transcription matches or is equivalent to the standard English spelling of the same item.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1835919b08190ba78e182b87358d4 |
completed | April 29, 2026, 4:04 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9cd5488190bcd23183179f48cd |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 17, 2026, 3:51 p.m.