Triple
T30344739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roy Mustang |
E771841
|
entity |
| Predicate | seeksToAtoneFor |
P41224
|
FINISHED |
| Object | actions in the Ishval Civil War |
—
|
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: actions in the Ishval Civil War | Statement: [Roy Mustang, seeksToAtoneFor, actions in the Ishval Civil War]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seeksToAtoneFor Context triple: [Roy Mustang, seeksToAtoneFor, actions in the Ishval Civil War]
-
A.
repentsFor
Indicates that one entity feels remorse or regret for an action, wrongdoing, or harm related to another entity.
-
B.
demandedAtonementFrom
Indicates that one entity required another to make amends or provide compensation for a perceived wrong or offense.
-
C.
soughtPardonFor
Indicates that one entity requested or attempted to obtain a formal pardon or forgiveness for another entity or for a specific action.
-
D.
seeksRedemption
chosen
Indicates that an entity is actively striving to atone for past wrongs or failures and restore its moral standing.
-
E.
penance
Indicates an act of self-imposed suffering, discipline, or reparation performed to atone for a wrongdoing or moral failing.
- 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_69f2248b9a208190bc3e6804acd5afd6 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f682065a548190bff089d7dafbf3ad |
completed | May 2, 2026, 11 p.m. |
| PD | Predicate disambiguation | batch_69f67603526c81908295a1ece8727c66 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:55 p.m.