Triple
T16945149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Corpus Christi Basilica |
E411048
|
entity |
| Predicate | district |
P2709
|
FINISHED |
| Object | Kazimierz |
E84107
|
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: Kazimierz | Statement: [Corpus Christi Basilica, district, Kazimierz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kazimierz Context triple: [Corpus Christi Basilica, district, Kazimierz]
-
A.
Kazimierz
chosen
Kazimierz is a historic district of Kraków known for its rich Jewish heritage, medieval architecture, and vibrant cultural life.
-
B.
Wacław
Wacław is a Polish given name, equivalent to the name Wenceslaus or Wenzel in other Central European languages.
-
C.
Wincentówek
Wincentówek is a small village located within the administrative district of Gmina Leoncin in east-central Poland.
-
D.
Zawisza Bydgoszcz
Zawisza Bydgoszcz is a Polish multi-sports club best known for its football team, based in the city of Bydgoszcz.
-
E.
Bronisław
Bronisław is a masculine Slavic given name, particularly common in Poland, borne by several notable historical and cultural figures.
- 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_69d886c886688190967be07322597ac9 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cfb14b788190be5b7f9c00c3e7ea |
completed | April 18, 2026, 6:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d46036108190a3ed8cb9f80c47fb |
completed | May 10, 2026, 6:54 p.m. |
Created at: April 10, 2026, 5:31 a.m.