Triple
T22969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winter War |
E456
|
entity |
| Predicate | hasCasualties |
P1399
|
FINISHED |
| Object | heavy casualties on both sides |
—
|
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: heavy casualties on both sides | Statement: [Winter War, hasCasualties, heavy casualties on both sides]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCasualties Context triple: [Winter War, hasCasualties, heavy casualties on both sides]
-
A.
casualties
chosen
Indicates that an event, action, or situation resulted in people being killed or injured.
-
B.
casualtiesEstimate
Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
-
C.
casualtiesKilledUS
Indicates that the relationship specifies the number of U.S. individuals who were killed as casualties in an event or incident.
-
D.
casualtiesJapan
Indicates that an event or action resulted in casualties (deaths and/or injuries) occurring in Japan.
-
E.
notableVictim
Indicates that the subject is a person or entity who is notably recognized as a victim of the object (such as an event, crime, or harmful 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_69a243b4ac2c8190b93c303df797b7b2 |
completed | Feb. 28, 2026, 1:24 a.m. |
| NER | Named-entity recognition | batch_69a246e94ca881908f7a7d2c0b293033 |
completed | Feb. 28, 2026, 1:37 a.m. |
| PD | Predicate disambiguation | batch_69a24654724481909ba14b7f68d2a472 |
completed | Feb. 28, 2026, 1:35 a.m. |
Created at: Feb. 28, 2026, 1:34 a.m.