Triple
T37808996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Opequon |
E942582
|
entity |
| Predicate | UnionCavalryCommander |
P189239
|
FINISHED |
| Object | Alfred T. A. Torbert |
—
|
NE NERFINISHED |
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: Alfred T. A. Torbert | Statement: [Battle of Opequon, UnionCavalryCommander, Alfred T. A. Torbert]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: UnionCavalryCommander Context triple: [Battle of Opequon, UnionCavalryCommander, Alfred T. A. Torbert]
-
A.
UnionCommanderOfAssault
Indicates that the subject served as the commanding Union officer in charge of a specific military assault.
-
B.
MongolianCommander
Indicates that an individual holds a commanding or leadership role within a Mongolian military or armed force context.
-
C.
TexianCommander
Indicates that an entity serves as a military commander for Texian forces in a given context or event.
-
D.
RepublicanCommander
Indicates that an individual serves as a military commander for the Republican side in a conflict.
-
E.
commanderOfVictoriousSide
Indicates that one entity served as the commanding leader of the side that achieved victory in a conflict or competition relative to another entity.
- F. None of above. chosen
Provenance (4 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_69f76ee8104c8190ab17133ccd8f86e6 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbb9e8108c8190ae1c7940b1677e95 |
completed | May 6, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fbb141605c8190b9c27d70352522db |
completed | May 6, 2026, 9:23 p.m. |
| PDg | Predicate description generation | batch_69fbb9e69b7481909beaf8264d87c5e5 |
completed | May 6, 2026, 10 p.m. |
Created at: May 3, 2026, 4:19 p.m.