Triple
T1091021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Shiloh |
E24161
|
entity |
| Predicate | estimatedConfederateCasualties |
P661
|
FINISHED |
| Object | about 10,000 |
—
|
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 10,000 | Statement: [Battle of Shiloh, estimatedConfederateCasualties, about 10,000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estimatedConfederateCasualties Context triple: [Battle of Shiloh, estimatedConfederateCasualties, about 10,000]
-
A.
casualtiesUnitedStates
Indicates that the event or situation resulted in casualties (deaths and/or injuries) among United States personnel or citizens.
-
B.
opponentInAmericanCivilWar
Indicates that two entities were on opposing sides in the American Civil War.
-
C.
positionWithinConfederacy
Indicates that one entity holds a specific role, rank, or status within a confederated group or alliance of entities.
-
D.
casualtiesEstimate
chosen
Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
-
E.
casualties
Indicates that an event, action, or situation resulted in people being killed or injured.
- 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b980c8448190b08c3a9a7e7f4e85 |
completed | March 1, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69a4b741b0cc8190be001a16a81f6d9e |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.