Triple
T10948958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 10 Armia (Niemcy) |
E258673
|
entity |
| Predicate | formacja |
P96790
|
FINISHED |
| Object | armia niemiecka okresu II wojny światowej |
—
|
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: armia niemiecka okresu II wojny światowej | Statement: [10 Armia (Niemcy), formacja, armia niemiecka okresu II wojny światowej]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formacja Context triple: [10 Armia (Niemcy), formacja, armia niemiecka okresu II wojny światowej]
-
A.
typeOfInformation
Indicates that one entity specifies the category or kind of information that characterizes or describes another entity.
-
B.
providesInformationIn
Indicates that one entity supplies or conveys information within or through another entity or context.
-
C.
providedInformationOn
Indicates that one entity supplied or communicated specific information or details to another entity.
-
D.
providedInformationTo
Indicates that one entity has supplied or communicated information to another entity.
-
E.
fact
Indicates that something is objectively true or has actually occurred, independent of opinion or belief.
- F. None of above. chosen
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_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. |
| PDg | Predicate description generation | batch_69d7322370648190ba14cdd6fb4cdcb0 |
completed | April 9, 2026, 4:59 a.m. |
Created at: April 8, 2026, 9:23 p.m.