Triple

T17075518
Position Surface form Disambiguated ID Type / Status
Subject Jovan Cvijić E414336 entity
Predicate familyName P18 FINISHED
Object Cvijić E414336 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: Cvijić | Statement: [Jovan Cvijić, familyName, Cvijić]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cvijić
Context triple: [Jovan Cvijić, familyName, Cvijić]
  • A. Cvijić chosen
    Cvijić is a Serbian surname most prominently associated with the renowned geographer and ethnologist Jovan Cvijić.
  • B. Vasojevići
    Vasojevići are one of the largest and historically significant Montenegrin tribes, traditionally inhabiting the northeastern highland region of Montenegro.
  • C. Ćićevac
    Ćićevac is a small town and municipality in central Serbia, situated in the Rasina District.
  • D. Boroević
    Boroević is a South Slavic surname most notably associated with Austro-Hungarian field marshal Svetozar Boroević, a prominent military commander during World War I.
  • E. Barilović
    Barilović is a small rural municipality and settlement in central Croatia, located within Karlovac County.
  • 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbc47808819088a4ca039689b213 completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a014140722481909f976e32597a873d completed May 11, 2026, 2:38 a.m.
Created at: April 10, 2026, 5:34 a.m.