Triple
T14890334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zalău |
E359737
|
entity |
| Predicate | roadConnectionTo |
P9041
|
FINISHED |
| Object | Satu Mare |
E123254
|
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: Satu Mare | Statement: [Zalău, roadConnectionTo, Satu Mare]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Satu Mare Context triple: [Zalău, roadConnectionTo, Satu Mare]
-
A.
Satu Mare
chosen
Satu Mare is a city in northwestern Romania near the Hungarian border, known as a regional economic and cultural center with a diverse ethnic heritage.
-
B.
Crișana
Crișana is a historical region in western Romania, known for its multicultural heritage and location between the Apuseni Mountains and the Hungarian border.
-
C.
Piatra Neamț
Piatra Neamț is a historic city in northeastern Romania, known for its picturesque setting in the Carpathian foothills and rich cultural heritage.
-
D.
Piatra-Olt
Piatra-Olt is a small town in southern Romania known as a local railway junction and administrative center within Olt County.
-
E.
Cisnădie
Cisnădie is a small town in central Romania’s Sibiu County, known for its historic fortified church and traditional Transylvanian character.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded5f883288190af602633fa7d6860 |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe72b11584819084f32516cb0023a1 |
completed | May 8, 2026, 11:33 p.m. |
Created at: April 10, 2026, 2:09 a.m.