Triple
T10120789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Prussia |
E223281
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Elbląg |
E330705
|
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: Elbląg | Statement: [Royal Prussia, contains, Elbląg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elbląg Context triple: [Royal Prussia, contains, Elbląg]
-
A.
Elbląg
chosen
Elbląg is a historic city in northern Poland known for its reconstructed Old Town, medieval heritage, and role as an important port and industrial center.
-
B.
Koszalin
Koszalin is a city in northwestern Poland near the Baltic Sea, known as a regional cultural and economic center.
-
C.
Bydgoszcz
Bydgoszcz is a major city in northern Poland known as an important economic, cultural, and academic center on the Brda and Vistula rivers.
-
D.
Kwidzyn
Kwidzyn is a historic town in northern Poland known for its medieval Teutonic castle complex and Gothic cathedral.
-
E.
Serock
Serock is a locality situated near the Western Bug River in eastern Europe.
- 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_69ca8422047c81909d66b717b8b18cf3 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd266b18c8190b35fe637c912e756 |
completed | April 2, 2026, 2:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f62d41448190ab65fb9c81d4d673 |
completed | May 2, 2026, 1:03 p.m. |
Created at: March 30, 2026, 9:04 p.m.