Triple
T16164708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Tupelo |
E392272
|
entity |
| Predicate | ConfederateCasualtiesTotal |
P34511
|
FINISHED |
| Object | approximately 1,300–1,400 |
—
|
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: approximately 1,300–1,400 | Statement: [Battle of Tupelo, ConfederateCasualtiesTotal, approximately 1,300–1,400]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ConfederateCasualtiesTotal Context triple: [Battle of Tupelo, ConfederateCasualtiesTotal, approximately 1,300–1,400]
-
A.
confederateCasualtiesAndLosses
chosen
Indicates the number or extent of casualties and material losses suffered by Confederate forces in a conflict or engagement.
-
B.
casualtiesTotal
Indicates the total number of people killed and injured as a result of a particular event or incident.
-
C.
hasConfederateBurialCount
Indicates the number of Confederate burials associated with a given entity or site.
-
D.
confederatePrisonersTaken
Indicates that one party has captured and taken prisoners who are affiliated with or fighting for the Confederate side.
-
E.
UScasualties
Indicates the number or occurrence of casualties suffered by the United States in a given conflict, event, or situation.
- 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_69d87f1d32208190942e4e499a80c18c |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21e622ae481909f3cf25b38886d3a |
completed | April 17, 2026, 11:49 a.m. |
| PD | Predicate disambiguation | batch_69e1828abb608190a99d86bce1d77de2 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5:02 a.m.