Triple
T20616952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michigan Civil War regiments |
E506590
|
entity |
| Predicate | casualtiesIncurred |
P1399
|
FINISHED |
| Object | killed in action |
—
|
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: killed in action | Statement: [Michigan Civil War regiments, casualtiesIncurred, killed in action]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: casualtiesIncurred Context triple: [Michigan Civil War regiments, casualtiesIncurred, killed in action]
-
A.
casualties
chosen
Indicates that an event, action, or situation resulted in people being killed or injured.
-
B.
casualtiesInflictedOn
Indicates that one party has caused deaths or injuries to another party as a result of a harmful event or action.
-
C.
casualtiesIncluded
Indicates that the referenced count or report of casualties explicitly includes the specified individuals or groups.
-
D.
sustainedHeavyCasualtiesAt
Indicates that an entity experienced a large number of serious losses (e.g., deaths or injuries) at a specific location or during a specific event.
-
E.
battleCasualty
Indicates that an entity was killed, wounded, or otherwise harmed as a direct result of a specific battle or armed conflict.
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aadd30b88190af3a05527ad5ac64 |
completed | April 20, 2026, 10:38 p.m. |
| PD | Predicate disambiguation | batch_69e5a00c43308190b7ea58d559257e07 |
completed | April 20, 2026, 3:39 a.m. |
Created at: April 16, 2026, 11:41 a.m.