Triple
T12372540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westerplatte Monument |
E295037
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | Adam Haupt |
E295037
|
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: Adam Haupt | Statement: [Westerplatte Monument, architect, Adam Haupt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adam Haupt Context triple: [Westerplatte Monument, architect, Adam Haupt]
-
A.
Adam Haupt
Adam Haupt is a designer known for creating the memorial at the former Nazi extermination camp Treblinka in Poland.
-
B.
Adam Haupt
chosen
Adam Haupt was a Polish sculptor and architect best known for co-designing the monumental Westerplatte Monument in Gdańsk commemorating the defenders of the Westerplatte peninsula in World War II.
-
C.
William Winde
William Winde was a 17th-century English architect and designer known for his work on grand country houses and royal residences.
-
D.
Thomas Eiskirch
Thomas Eiskirch is a German politician who serves as the lord mayor of the city of Bochum in North Rhine-Westphalia.
-
E.
Alfred Gunzenhauser
Alfred Gunzenhauser was a German art collector whose extensive collection of modern art became the foundation of the Museum Gunzenhauser in Chemnitz.
- 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_69d6ab6d8a4081908636601e69ddf262 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93fa7c9ec81908c685612994543e3 |
completed | April 10, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62abfd9c081909803691d3fc4f149 |
completed | May 2, 2026, 4:48 p.m. |
Created at: April 8, 2026, 9:54 p.m.