Triple
T20483265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salzburger Land |
E502517
|
entity |
| Predicate | hasLake |
P1025
|
FINISHED |
| Object | Wallersee |
E625338
|
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: Wallersee | Statement: [Salzburger Land, hasLake, Wallersee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wallersee Context triple: [Salzburger Land, hasLake, Wallersee]
-
A.
Wallersee
chosen
Wallersee is a scenic lake in the Austrian state of Salzburg, popular for recreation and nature activities.
-
B.
Wiesener
Wiesener is a surname, likely of German origin, that serves as a variant spelling of the name Wiesner.
-
C.
Vohenstrauß
Vohenstrauß is a small town in the Upper Palatinate region of Bavaria, Germany, known for its historic architecture and surrounding forested landscapes.
-
D.
Traun
Traun is a town in the Austrian state of Upper Austria, located near Linz along the Traun River and known as a residential and industrial suburb of the regional capital.
-
E.
Traun
Traun is a river in southeastern Germany that flows through the Chiemgau region of Bavaria.
- 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_69e0b4af32848190aea80682b44d5d6e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69b58c4b4819083d0ba2397dbfb0b |
completed | April 20, 2026, 9:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08accee0688190a897ed76719a977d |
completed | May 16, 2026, 5:43 p.m. |
Created at: April 16, 2026, 11:34 a.m.