Triple
T12354324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kyustendil Province |
E294568
|
entity |
| Predicate | hasTown |
P847
|
FINISHED |
| Object | Dupnitsa |
E430944
|
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: Dupnitsa | Statement: [Kyustendil Province, hasTown, Dupnitsa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dupnitsa Context triple: [Kyustendil Province, hasTown, Dupnitsa]
-
A.
Dupnitsa
chosen
Dupnitsa is a town in southwestern Bulgaria known as a regional center near the Osogovo Mountains, with historical roots and access to mountain tourism and outdoor activities.
-
B.
Karmanovo
Karmanovo is a rural village located within the Gagarinsky District of Smolensk Oblast in western Russia.
-
C.
Tsarevo
Tsarevo is a coastal town and popular seaside resort on the Black Sea in southeastern Bulgaria.
-
D.
Pliska
Pliska was the first capital city of the early medieval First Bulgarian Empire, serving as its political and administrative center.
-
E.
Černilov
Černilov is a municipality and village in the Hradec Králové Region of the Czech Republic, known for its rural character and proximity to the city of Hradec Králové.
- 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f8bc60c8190b0ceb84093e70db4 |
completed | April 10, 2026, 6:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f64b90779881909893d1e6877ce567 |
completed | May 2, 2026, 7:08 p.m. |
Created at: April 8, 2026, 9:54 p.m.