Triple
T10948899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | bitwa pod Kutnem |
E258672
|
entity |
| Predicate | część |
P45787
|
FINISHED |
| Object | kampania wrześniowa |
—
|
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: kampania wrześniowa | Statement: [bitwa pod Kutnem, część, kampania wrześniowa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: część Context triple: [bitwa pod Kutnem, część, kampania wrześniowa]
-
A.
partOfSingle
Indicates that one entity is a component or member of exactly one specific whole or collection, and not shared among multiple such wholes.
-
B.
partOfType
chosen
Indicates that one entity represents a component, segment, or subset that belongs to or is included within the type or category represented by another entity.
-
C.
partlyConsistsOf
Indicates that one entity is composed in part, but not entirely, of another entity.
-
D.
deltaPartOf
Indicates that one entity represents a changed, differing, or modified portion of another entity, rather than the whole.
-
E.
partUsed
Indicates that one entity is a component or part that is utilized in the construction, operation, or composition of another entity.
- 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_69d6aa88500c819097d7032ca578e74f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d770ec7028819084f5ce2035a128e4 |
completed | April 9, 2026, 9:27 a.m. |
| PD | Predicate disambiguation | batch_69d72e816a98819096d6c10dfb88a66a |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:23 p.m.