Triple
T25402422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ковальский |
E636460
|
entity |
| Predicate | происхождение |
P54889
|
FINISHED |
| Object | польская фамилия Kowalski |
—
|
LITERAL 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: польская фамилия Kowalski | Statement: [Ковальский, происхождение, польская фамилия Kowalski]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: происхождение Context triple: [Ковальский, происхождение, польская фамилия Kowalski]
-
A.
historicalOriginMeaning
chosen
Indicates that one entity explains the original historical source or derivational meaning of another entity.
-
B.
historicalOrigin
Indicates the relationship by which one entity serves as the source, origin, or starting point in history for another entity.
-
C.
originatesAs
Indicates that one entity begins, arises, or comes into existence in the form, state, or role specified by another entity.
-
D.
describesOriginOf
Indicates that one entity specifies or explains the source, provenance, or origin of another entity.
-
E.
proposedAsAncestralOriginOf
Indicates that something is suggested or hypothesized to be the ancestral source or origin of something else.
- 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_69e75db361d881908d8701c856da6413 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f584fbde0c8190ac451fe33848aadb |
completed | May 2, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_69f45d0dbc8c8190beecce679fce90a4 |
completed | May 1, 2026, 7:58 a.m. |
Created at: April 21, 2026, 1:52 p.m.