Triple
T21514291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Piaski |
E530803
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | Piaski, Krynica Morska |
—
|
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: Piaski, Krynica Morska | Statement: [Piaski, hasAlternativeName, Piaski, Krynica Morska]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Piaski, Krynica Morska Context triple: [Piaski, hasAlternativeName, Piaski, Krynica Morska]
-
A.
Piaski
chosen
Piaski is a small Polish coastal village situated on the Vistula Spit near the border with Russia’s Kaliningrad Oblast.
-
B.
Piaski
Piaski is a town in eastern Poland that serves as a local transport hub and junction point for regional roads and expressways.
-
C.
Kościerzyna
Kościerzyna is a historic town in northern Poland known as a local cultural and economic center within the Kashubian region.
-
D.
Wrzeszcz
Wrzeszcz is a central district of Gdańsk, Poland, known as a major residential, commercial, and transport hub of the city.
-
E.
Gryfice
Gryfice is a historic town in northwestern Poland known for its medieval urban layout and remnants of defensive walls.
- 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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea88e6fc8190a4b73b8d32dae5a8 |
completed | April 23, 2026, 9:46 a.m. |
Created at: April 16, 2026, 6:25 p.m.