Triple
T6051444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savannah Campaign |
E134802
|
entity |
| Predicate | UnionForceSize |
P6153
|
FINISHED |
| Object | about 62,000 soldiers |
—
|
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: about 62,000 soldiers | Statement: [Savannah Campaign, UnionForceSize, about 62,000 soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: UnionForceSize Context triple: [Savannah Campaign, UnionForceSize, about 62,000 soldiers]
-
A.
unionArmy
Indicates that an entity served in, was part of, or is otherwise affiliated with the Union Army (the United States Army of the North) during the American Civil War.
-
B.
forceSizeConfederate
Indicates that one entity compels or influences another (the confederate) to adopt or present a particular physical size or size-related appearance.
-
C.
USForces
Indicates the presence, involvement, or deployment of United States military forces in relation to a specified location, event, or entity.
-
D.
numberOfTroopsInvolved
chosen
Indicates the quantity of military personnel participating in or assigned to a specific operation, event, or engagement.
-
E.
USForceType
Indicates the type or category of U.S. military force involved in a given relationship 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_69c00877b6d4819096b0e163728b73a3 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c056f802988190aafdb7cbb087c828 |
completed | March 22, 2026, 8:54 p.m. |
| PD | Predicate disambiguation | batch_69c049edc6f0819092ca620d9073ad26 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:09 p.m.