Triple
T17614377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sea Towers |
E429044
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | Andrzej Kapuścik |
—
|
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: Andrzej Kapuścik | Statement: [Sea Towers, architect, Andrzej Kapuścik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrzej Kapuścik Context triple: [Sea Towers, architect, Andrzej Kapuścik]
-
A.
Andrzej Kapuścik
chosen
Andrzej Kapuścik is a Polish architect best known for designing the prominent Sea Towers skyscraper complex in Gdynia, Poland.
-
B.
Andrzej Korzyński
Andrzej Korzyński was a Polish composer best known for his innovative and atmospheric film scores, particularly in European cinema of the 1970s and 1980s.
-
C.
Andrzej Ryżewski
Andrzej Ryżewski is a Polish academic who has served as the rector of the University of Białystok.
-
D.
Andrzej Pelczar
Andrzej Pelczar was a Polish mathematician known for his contributions to functional analysis and for his academic work in the Polish school of mathematics.
-
E.
Zbigniew Kadłubek
Zbigniew Kadłubek is a Polish writer, essayist, and scholar known for his significant contributions to contemporary Silesian-language literature and culture.
- 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46d2fd96481908c9f3b566fca6907 |
completed | April 19, 2026, 5:50 a.m. |
Created at: April 10, 2026, 5:51 a.m.