Triple
T1087844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vistula River |
E24092
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object | Sandomierz |
E198380
|
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: Sandomierz | Statement: [Vistula River, flowsThrough, Sandomierz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandomierz Context triple: [Vistula River, flowsThrough, Sandomierz]
-
A.
Sandomierz
chosen
Sandomierz is a historic town in southeastern Poland, known for its well-preserved Old Town, medieval architecture, and picturesque location on the Vistula River.
-
B.
Wadowice
Wadowice is a historic town in southern Poland best known as the birthplace of Pope John Paul II.
-
C.
Nowy Sącz
Nowy Sącz is a historic city in southern Poland known for its well-preserved Old Town, cultural heritage, and role as a local economic and administrative center.
-
D.
Tarnobrzeg
Tarnobrzeg is a city in southeastern Poland known historically for its sulfur mining industry and location along the Vistula River.
-
E.
Tarnów
Tarnów is a historic city in southern Poland known for its well-preserved Old Town, Renaissance architecture, and cultural heritage.
- 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b97c64a88190bf1119fdd4940bf3 |
completed | March 1, 2026, 10:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae0a966a6c81909d1d21c489340134 |
completed | March 8, 2026, 11:47 p.m. |
Created at: March 1, 2026, 7:42 p.m.