Triple
T9190459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banie Mazurskie |
E220572
|
entity |
| Predicate | hasVoivodeshipCapital |
P84126
|
FINISHED |
| Object | Olsztyn |
—
|
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: Olsztyn | Statement: [Banie Mazurskie, hasVoivodeshipCapital, Olsztyn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVoivodeshipCapital Context triple: [Banie Mazurskie, hasVoivodeshipCapital, Olsztyn]
-
A.
voivodeshipCapitalSince
Indicates that a location has served as the capital of a voivodeship (an administrative region) starting from a specified point in time.
-
B.
associatedWithVoivodeshipCapital
Indicates a relationship where something is linked or connected to the capital city of a voivodeship (a regional administrative unit).
-
C.
hasVoivode
Indicates that a region, territory, or administrative unit is governed or overseen by a specific voivode (provincial governor).
-
D.
hasVoivodeshipRights
Indicates that an entity possesses the legal status, privileges, or jurisdictional authority associated with a voivodeship (a regional administrative unit).
-
E.
associatedVoivodeship
chosen
Indicates that one entity is administratively or geographically linked to a specific voivodeship (province-level region).
- F. None of above.
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_69ca83e6d77c81909862b7afef56b1bf |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccd5bf25c081909e651b67ef8ecc33 |
completed | April 1, 2026, 8:22 a.m. |
| PD | Predicate disambiguation | batch_69cc66090e5881908889dc1213815626 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:24 p.m.