Triple
T7504048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of South Mountain |
E177339
|
entity |
| Predicate | unionCasualtiesApprox |
P28432
|
FINISHED |
| Object | over 2,000 killed, wounded, or missing |
—
|
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: over 2,000 killed, wounded, or missing | Statement: [Battle of South Mountain, unionCasualtiesApprox, over 2,000 killed, wounded, or missing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unionCasualtiesApprox Context triple: [Battle of South Mountain, unionCasualtiesApprox, over 2,000 killed, wounded, or missing]
-
A.
casualtiesEstimate
Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
-
B.
militaryCasualtiesEstimate
Indicates an estimated number of people killed, wounded, or missing as a result of military conflict or operations.
-
C.
nativeCasualties
Indicates that native or indigenous people suffered deaths or injuries as a result of a particular event, action, or conflict.
-
D.
UScasualties
chosen
Indicates the number or occurrence of casualties suffered by the United States in a given conflict, event, or situation.
-
E.
casualtiesUnion
Indicates a relationship where multiple casualty figures or reports are combined into a single aggregated total.
- 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_69c69f2696688190915a8458f2398211 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f81b431481908214b69c6c8d83bc |
completed | March 27, 2026, 9:35 p.m. |
| PD | Predicate disambiguation | batch_69c6f4d266d88190982cf5d2ee2e9564 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:44 p.m.