Triple
T35599616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metropolitan of Belgrade and Karlovci |
E1028729
|
entity |
| Predicate | usesTitleInSerbian |
P143423
|
FINISHED |
| Object | Митрополит београдско-карловачки |
—
|
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: Митрополит београдско-карловачки | Statement: [Metropolitan of Belgrade and Karlovci, usesTitleInSerbian, Митрополит београдско-карловачки]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesTitleInSerbian Context triple: [Metropolitan of Belgrade and Karlovci, usesTitleInSerbian, Митрополит београдско-карловачки]
-
A.
nameInSerbianCyrillic
Indicates that an entity’s name is written in the Serbian Cyrillic script.
-
B.
SerbianName
Indicates that an entity has a name that is of Serbian origin or used in the Serbian language.
-
C.
usesTitleIn
chosen
Indicates that an entity is referred to using a particular title within a specified context or medium.
-
D.
officeHolderTitleInSerbian
Indicates the official title or designation of an office holder expressed in the Serbian language.
-
E.
languageNameSerbianLatin
Indicates that the specified language name is written in Serbian using the Latin script.
- 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_69f76e0598dc8190a6a093e904b9aa70 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd09840ea88190a2e6d7e577ade717 |
completed | May 7, 2026, 9:52 p.m. |
| PD | Predicate disambiguation | batch_69fd064c49988190afadddbd04d7cb94 |
completed | May 7, 2026, 9:38 p.m. |
Created at: May 3, 2026, 4:05 p.m.