Triple
T11744017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Starogard Gdański |
E279225
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Maardu |
E491064
|
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: Maardu | Statement: [Starogard Gdański, hasTwinTown, Maardu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maardu Context triple: [Starogard Gdański, hasTwinTown, Maardu]
-
A.
Maardu
chosen
Maardu is an industrial town in northern Estonia, located just east of the capital Tallinn in Harju County.
-
B.
Pärnu
Pärnu is a coastal city in southwestern Estonia known as a popular summer resort and spa destination on the Baltic Sea.
-
C.
Tallinn
Tallinn is the capital and largest city of Estonia, a historic Baltic Sea port known for its well-preserved medieval Old Town and strategic maritime location.
-
D.
Tartu
Tartu is Estonia’s second-largest city and a historic cultural and intellectual center, best known as the country’s main university town.
-
E.
Kuressaare
Kuressaare is the main town on Estonia’s Saaremaa island, known for its well-preserved medieval castle and seaside spa resort atmosphere.
- 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_69d6ab01038c819080714901502c84fc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4f2a38c8190a682d8dae1ab9415 |
completed | April 10, 2026, 7:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f019e4f0988190afe0b92f4c9d8073 |
completed | April 28, 2026, 2:22 a.m. |
Created at: April 8, 2026, 9:41 p.m.