Triple
T9364907
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viljandi |
E225374
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Cēsis |
E498325
|
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: Cēsis | Statement: [Viljandi, hasTwinTown, Cēsis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cēsis Context triple: [Viljandi, hasTwinTown, Cēsis]
-
A.
Cēsis
chosen
Cēsis is a historic town in northern Latvia known for its medieval castle, well-preserved old town, and role in Latvian cultural and national history.
-
B.
Jekabpils
Jekabpils is a town in southeastern Latvia known for its historic architecture and scenic location along the Daugava River.
-
C.
Bauska
Bauska is a historic town in southern Latvia known for its medieval castle and location at the confluence of the Mūsa and Mēmele rivers, which form the Lielupe.
-
D.
Kuldīga
Kuldīga is a historic town in western Latvia known for its well-preserved old town and proximity to the Venta Rapid, one of Europe’s widest natural waterfalls.
-
E.
Rēzekne
Rēzekne is a city in eastern Latvia that serves as one of the main cultural, economic, and transportation centers of the Latgale region.
- 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_69ca842cbddc819099d71ecec48cf9e5 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd503fd7f081909655e2a880c84834 |
completed | April 1, 2026, 5:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0f3f3c420819084b65fd4537aaf93 |
completed | April 4, 2026, 11:20 a.m. |
Created at: March 30, 2026, 7:43 p.m.