Triple
T26593055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isaac Ingalls Stevens |
E667411
|
entity |
| Predicate | civilWarSide |
P35239
|
FINISHED |
| Object | Union |
—
|
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: Union | Statement: [Isaac Ingalls Stevens, civilWarSide, Union]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: civilWarSide Context triple: [Isaac Ingalls Stevens, civilWarSide, Union]
-
A.
memberSupportedSideInCivilWar
Indicates that a member or group actively backed, aligned with, or provided support to a particular side or faction in a civil war.
-
B.
unionArmy
chosen
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.
-
C.
conflictSide
Indicates that an entity participates as a distinct party or faction on one side of a conflict or dispute.
-
D.
civilWarTheater
Indicates a geographic or operational area where events of a civil war take place or are focused.
-
E.
opponentInAmericanCivilWar
Indicates that two entities were on opposing sides in the American Civil War.
- 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_69ee9cfc385081909ac9ae178030a06e |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f61527774c8190b62e748829565ebf |
completed | May 2, 2026, 3:15 p.m. |
| PD | Predicate disambiguation | batch_69f60b8bb0d08190ab5a9a2a8847c6f4 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 2:09 a.m.