Triple
T20242214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cēsis |
E498325
|
entity |
| Predicate | historicalName |
P65
|
FINISHED |
| Object | Wenden |
E1130395
|
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: Wenden | Statement: [Cēsis, historicalName, Wenden]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wenden Context triple: [Cēsis, historicalName, Wenden]
-
A.
Wenden
chosen
Wenden was a historic town in present-day Latvia that served as a major political and administrative center of the Duchy of Livonia.
-
B.
Wustrow
Wustrow is a small town in the Wendland region of Lower Saxony, Germany, known for its rural character and traditional half-timbered architecture.
-
C.
Retzow
Retzow is a small municipality in the Havelland district of the federal state of Brandenburg in northeastern Germany.
-
D.
Werneuchen
Werneuchen is a small town in the German state of Brandenburg, located northeast of Berlin and characterized by its rural surroundings and commuter links to the capital.
-
E.
Wrangelsburg
Wrangelsburg is a historic estate and locality in northeastern Germany associated with the 17th-century Swedish field marshal and statesman Carl Gustaf Wrangel.
- 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6716f9d248190a145f6883827ebbe |
completed | April 20, 2026, 6:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a084b9607b48190bc9c68c4e9b8f9b8 |
completed | May 16, 2026, 10:48 a.m. |
Created at: April 11, 2026, 11:40 p.m.