Triple
T233487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Suomussalmi |
E4457
|
entity |
| Predicate | SovietCasualties |
P661
|
FINISHED |
| Object | tens of thousands killed, wounded, or captured |
—
|
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: tens of thousands killed, wounded, or captured | Statement: [Battle of Suomussalmi, SovietCasualties, tens of thousands killed, wounded, or captured]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: SovietCasualties Context triple: [Battle of Suomussalmi, SovietCasualties, tens of thousands killed, wounded, or captured]
-
A.
militaryCasualtiesEstimate
Indicates an estimated number of people killed, wounded, or missing as a result of military conflict or operations.
-
B.
SovietAction
Indicates actions, policies, or interventions carried out by the Soviet Union or its authorities toward another entity.
-
C.
numberOfSovietPOWsVictimsEstimate
Indicates an estimated count of victims who were Soviet prisoners of war.
-
D.
casualtiesEstimate
chosen
Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
-
E.
casualtiesKilledUS
Indicates that the relationship specifies the number of U.S. individuals who were killed as casualties in an event or incident.
- 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_69a257363ffc81909757bde7ab3404da |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25f14f72081908182e76300b59358 |
completed | Feb. 28, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69a25b5c8c888190b5544e687736b373 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.