Triple
T21801443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Speaker of the National Assembly |
E538245
|
entity |
| Predicate | titleInSerbianLatin |
P89513
|
FINISHED |
| Object | Predsednik Narodne skupštine |
—
|
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: Predsednik Narodne skupštine | Statement: [Speaker of the National Assembly, titleInSerbianLatin, Predsednik Narodne skupštine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleInSerbianLatin Context triple: [Speaker of the National Assembly, titleInSerbianLatin, Predsednik Narodne skupštine]
-
A.
titleInLatinScript
Indicates that the title of an entity is written or represented using a Latin-based writing system.
-
B.
titleInLanguage
chosen
Indicates that a specific title or name is expressed in a particular language.
-
C.
titleInEnglish
Indicates that an entity’s title or name is given in the English language.
-
D.
titleInLocalLanguage
Indicates that an entity’s title is expressed in the primary or native language of a specified place or community.
-
E.
titleInRussian
Indicates that an entity’s title is given or recorded in the Russian language.
- 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_69e0c4733f4081909a86622e7e6d15d2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f077ff986081909c984cd190167640 |
completed | April 28, 2026, 9:03 a.m. |
| PD | Predicate disambiguation | batch_69e6be751ce881909badced245ef76c7 |
completed | April 21, 2026, 12:01 a.m. |
Created at: April 16, 2026, 6:53 p.m.