Triple
T8128470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serbian Army |
E189793
|
entity |
| Predicate | notableCommander |
P1197
|
FINISHED |
| Object | Petar Bojović |
E434963
|
NE 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: Petar Bojović | Statement: [Serbian Army, notableCommander, Petar Bojović]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Petar Bojović Context triple: [Serbian Army, notableCommander, Petar Bojović]
-
A.
Petar Bojović
chosen
Petar Bojović was a Serbian general and field marshal renowned for his leadership of Serbian forces in key Balkan and World War I campaigns.
-
B.
Zoran Živković
Zoran Živković is a Serbian politician who briefly served as the country's prime minister in the early 2000s following the assassination of Zoran Đinđić.
-
C.
Živojin Mišić
Živojin Mišić was a prominent Serbian field marshal and military strategist, renowned for his leadership in key Balkan and World War I battles.
-
D.
Predrag Bulatović
Predrag Bulatović is a Montenegrin politician known for leading the pro-union camp that opposed Montenegro’s independence from the State Union of Serbia and Montenegro.
-
E.
Vladan Đokić
Vladan Đokić is a Serbian architect and academic who serves as a leading figure in higher education at the University of Belgrade.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca82bcb4848190a9a9d036ad768642 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb439190d88190aa614445c7479353 |
completed | March 31, 2026, 3:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd3457196081909f739af8c17b4d4c |
completed | April 1, 2026, 3:05 p.m. |
Created at: March 30, 2026, 5:34 p.m.