Triple
T1983403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kosovo |
E43081
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Pristina |
E33983
|
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: Pristina | Statement: [Kosovo, capital, Pristina]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pristina Context triple: [Kosovo, capital, Pristina]
-
A.
Pristina
chosen
Pristina is the capital and largest city of Kosovo, serving as its political, economic, and cultural center in the central Balkans.
-
B.
Tirana
Tirana is the capital and largest city of Albania, serving as its political, economic, and cultural center in the Balkans.
-
C.
Skopje
Skopje is the capital and largest city of North Macedonia, known for its historic Ottoman and Byzantine heritage alongside extensive modern redevelopment.
-
D.
Podgorica
Podgorica is the capital and largest city of Montenegro, serving as its political, economic, and cultural center in the Balkans.
-
E.
Cetinje
Cetinje is a historic town in Montenegro that served as the country’s old royal capital and cultural center.
- 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_69a88713ddc88190a969715658ebe7a8 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb820815481908aac6d89b437225b |
completed | March 7, 2026, 5:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae03301a2481909f6147482d490b90 |
completed | March 8, 2026, 11:16 p.m. |
Created at: March 4, 2026, 7:37 p.m.