Triple
T12720616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Velikiye Luki |
E303967
|
entity |
| Predicate | garrisonDestroyed |
P106559
|
FINISHED |
| Object | German forces in Velikiye Luki |
—
|
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: German forces in Velikiye Luki | Statement: [Battle of Velikiye Luki, garrisonDestroyed, German forces in Velikiye Luki]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: garrisonDestroyed Context triple: [Battle of Velikiye Luki, garrisonDestroyed, German forces in Velikiye Luki]
-
A.
garrisonAttacked
Indicates that a military garrison was subjected to an attack by another force or entity.
-
B.
garrisonSurrenderedTo
Indicates that a defending military garrison formally capitulated and yielded control to another party.
-
C.
garrisonTown
Indicates that a town serves as a military base or station where armed forces are permanently or regularly housed.
-
D.
garrisonAfterEvacuation
Indicates that a military force is stationed in a location following a prior evacuation of that location.
-
E.
nearbySettlementDestroyed
Indicates that a settlement located close to a reference place has been destroyed.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96d89ea70819098c470344f172167 |
completed | April 10, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69d96403957c81909acdee7bdae71696 |
completed | April 10, 2026, 8:56 p.m. |
| PDg | Predicate description generation | batch_69d96d87078c819083ea724238992204 |
completed | April 10, 2026, 9:37 p.m. |
Created at: April 9, 2026, 5:24 p.m.