Triple
T21183361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roosendaal |
E522007
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Gorlice |
—
|
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: Gorlice | Statement: [Roosendaal, hasTwinTown, Gorlice]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gorlice Context triple: [Roosendaal, hasTwinTown, Gorlice]
-
A.
Gorlice
chosen
Gorlice is a historic town in southern Poland known for its role in the World War I Battle of Gorlice–Tarnów and its early oil industry.
-
B.
Gröditz
Gröditz is a small industrial town in the German state of Saxony, known historically for its steel production.
-
C.
Drohiczyn
Drohiczyn is a historic town in eastern Poland, picturesquely situated on the Bug River and known for its rich cultural and religious heritage.
-
D.
Kraśnik
Kraśnik is a town in eastern Poland known for its historical architecture and location within the Lublin region.
-
E.
Otwock
Otwock is a town in east-central Poland known as a suburban spa and residential area within the broader Warsaw region.
- 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_69e0b50ef1d48190b063aa342667df22 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7301f7f1c81908686866fdee57127 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 3:05 p.m.