Triple
T20087362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of the Black Madonna |
E496169
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | Josef Gočár |
—
|
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: Josef Gočár | Statement: [House of the Black Madonna, architect, Josef Gočár]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Josef Gočár Context triple: [House of the Black Madonna, architect, Josef Gočár]
-
A.
Josef Gočár
chosen
Josef Gočár was a prominent Czech architect of the early 20th century, known for his influential contributions to Cubist and modernist architecture in Czechoslovakia.
-
B.
Pavel Zdráhal
Pavel Zdráhal is a Czech ice hockey player known for his professional career in European leagues.
-
C.
Tomáš Vlasák
Tomáš Vlasák is a Czech former professional ice hockey forward known for his successful career in European leagues and appearances with the Czech national team.
-
D.
Kamil Kuča
Kamil Kuča is a Czech academic and scientist who serves as the rector of the University of Hradec Králové.
-
E.
Petr Sýkora
Petr Sýkora is a Czech former professional ice hockey forward best known for his long NHL career, including Stanley Cup wins with the New Jersey Devils and Pittsburgh Penguins.
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655c7de081909a400c736e92495d |
completed | April 20, 2026, 5:41 p.m. |
Created at: April 11, 2026, 11:13 p.m.