Triple
T3954910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brusilov Offensive |
E84952
|
entity |
| Predicate | RussianLosses |
P6773
|
FINISHED |
| Object | hundreds of thousands of casualties |
—
|
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: hundreds of thousands of casualties | Statement: [Brusilov Offensive, RussianLosses, hundreds of thousands of casualties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: RussianLosses Context triple: [Brusilov Offensive, RussianLosses, hundreds of thousands of casualties]
-
A.
SovietEquipmentLosses
Indicates the extent or instances of military equipment lost by Soviet forces in a given conflict or period.
-
B.
SovietOperation
Indicates that an operation, mission, or organized activity is conducted by, on behalf of, or under the authority of the Soviet Union or its institutions.
-
C.
RussianObjective
Indicates that an entity has an objective, goal, or target specifically related to Russia (e.g., Russian interests, territory, institutions, or actors).
-
D.
militaryCasualtiesEstimate
chosen
Indicates an estimated number of people killed, wounded, or missing as a result of military conflict or operations.
-
E.
involvedUnitSoviet
Indicates that a Soviet military or organizational unit was involved in a particular event, operation, or action.
- 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_69aed934fbfc8190847068e4546de963 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefaa5afdc8190b709af2473d75d02 |
completed | March 9, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69aef8ed04e4819096bced8971cd888d |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:30 p.m.