Triple
T26359554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bitwa pod Kockiem |
E660161
|
entity |
| Predicate | casualtiesGermanyApprox |
P14574
|
FINISHED |
| Object | ok. 1000 zabitych i rannych |
—
|
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: ok. 1000 zabitych i rannych | Statement: [Bitwa pod Kockiem, casualtiesGermanyApprox, ok. 1000 zabitych i rannych]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: casualtiesGermanyApprox Context triple: [Bitwa pod Kockiem, casualtiesGermanyApprox, ok. 1000 zabitych i rannych]
-
A.
casualtiesGermanWounded
Indicates that the relationship specifies the number of German individuals who were wounded (but not killed) as casualties in a particular event or context.
-
B.
numberOfGermanVictims
chosen
Indicates the quantity of victims who are identified as German in the context of the described event or situation.
-
C.
GermanLoss
Indicates that Germany experiences a loss, defeat, or negative outcome in the specified context or event.
-
D.
militaryCasualtiesSide
Indicates the side or party in a conflict to which the recorded military casualties belong.
-
E.
casualtiesCountry
Indicates that the specified country is the one in which the recorded casualties (deaths or injuries) occurred or to which those casualties belong.
- 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_69ee8126d52c8190bc0b34337c2c9aa8 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f612607c388190ab61d1ac7d18e08d |
completed | May 2, 2026, 3:04 p.m. |
| PD | Predicate disambiguation | batch_69f611a9272881909093360472be832c |
completed | May 2, 2026, 3 p.m. |
Created at: April 26, 2026, 10:50 p.m.