Triple
T35803837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pewelka |
E1035053
|
entity |
| Predicate | countrySubdivisionLevel3 |
P46121
|
FINISHED |
| Object | Gmina Stryszawa |
E317987
|
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: Gmina Stryszawa | Statement: [Pewelka, countrySubdivisionLevel3, Gmina Stryszawa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countrySubdivisionLevel3 Context triple: [Pewelka, countrySubdivisionLevel3, Gmina Stryszawa]
-
A.
countrySubdivision
Indicates that one geopolitical region is an administrative or territorial subdivision of a larger country.
-
B.
countrySubdivisionType
Indicates the specific type or category of an administrative or territorial subdivision within a country (e.g., state, province, region).
-
C.
lowerLevelSubdivision
chosen
Indicates that one administrative or organizational unit is a smaller, subordinate subdivision within another, higher-level unit.
-
D.
realmSubdivision
Indicates a hierarchical relationship where one realm is a constituent subdivision or part of a larger realm.
-
E.
coordinatesCountrySubdivision
Indicates that one entity is responsible for organizing, managing, or overseeing the administrative or operational aspects of a specific country subdivision.
- F. None of above.
Provenance (4 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_69f76e169bd081909f16cd8c9ee7870c |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a020ab9630c8190a55efd5704cc6043 |
completed | May 11, 2026, 4:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a390d2d5e708190a3e9e4e73e3b4bd9 |
completed | June 22, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_6a020800e2b88190a1a37e710d8c92bf |
completed | May 11, 2026, 4:46 p.m. |
Created at: May 3, 2026, 4:06 p.m.