Triple
T13097686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andreas Karlstadt |
E310632
|
entity |
| Predicate | workLocation |
P7
|
FINISHED |
| Object | Orlamünde |
E693405
|
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: Orlamünde | Statement: [Andreas Karlstadt, workLocation, Orlamünde]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Orlamünde Context triple: [Andreas Karlstadt, workLocation, Orlamünde]
-
A.
Orlamünde
chosen
Orlamünde is a small historic town in the German state of Thuringia, situated along the Saale River.
-
B.
Orlem
Orlem is a prominent residential neighborhood in the Malad suburb of Mumbai, known for its churches, schools, and bustling local markets.
-
C.
Vendryně
Vendryně is a village in the Moravian-Silesian Region of the Czech Republic, known for its location in the historical region of Cieszyn Silesia near the Olza River.
-
D.
Flerzheim
Flerzheim is a village and district of the town of Rheinbach in the Rhein-Sieg-Kreis region of North Rhine-Westphalia, Germany.
-
E.
Ländtor
Ländtor is a historic city gate in Landshut, Germany, known as one of the town’s most prominent medieval landmarks.
- 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_69d806a733548190989cfd4ce981ca33 |
completed | April 9, 2026, 8:05 p.m. |
| NER | Named-entity recognition | batch_69d9814e88a0819088418c792ce7aa57 |
completed | April 10, 2026, 11:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6d619b82c819093d0d98db88eb9ae |
completed | May 3, 2026, 4:59 a.m. |
Created at: April 9, 2026, 9:04 p.m.