Triple
T21969246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hans von Marées |
E542541
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Hans von Marées |
—
|
NE NERFINISHED |
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: Hans von Marées | Statement: [Hans von Marées, name, Hans von Marées]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hans von Marées Context triple: [Hans von Marées, name, Hans von Marées]
-
A.
Hans von Marées
chosen
Hans von Marées was a 19th-century German painter known for his monumental mural works and idealized, often mythological figure compositions.
-
B.
Théodore Hanssen
Théodore Hanssen was a stained-glass artist known for creating notable windows, including works in Metz Cathedral.
-
C.
Gerhard von der Ahé
Gerhard von der Ahé was the adopted brother of Gudrun Himmler, the daughter of leading Nazi official Heinrich Himmler.
-
D.
Hugo von Pohl
Hugo von Pohl was a German admiral who served as a senior naval leader of the Imperial German Navy during World War I.
-
E.
Hans von Lossberg
Hans von Lossberg was a German military officer known for his service as a staff officer and strategist during World War I.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c48070988190909db97667b9a0ac |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1245d50d08190a4bf93139daa77eb |
completed | April 28, 2026, 9:19 p.m. |
Created at: April 16, 2026, 8:02 p.m.