Triple
T26168053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marianna raid |
E654310
|
entity |
| Predicate | woundedCommander |
P114087
|
FINISHED |
| Object | Alexander Asboth was severely wounded |
—
|
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: Alexander Asboth was severely wounded | Statement: [Marianna raid, woundedCommander, Alexander Asboth was severely wounded]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: woundedCommander Context triple: [Marianna raid, woundedCommander, Alexander Asboth was severely wounded]
-
A.
wasWoundedIn
Indicates that an entity sustained an injury as a result of a specified event, situation, or conflict.
-
B.
woundedAt
chosen
Indicates that an entity was injured or harmed at a specific place or during a particular event.
-
C.
casualtiesWounded
Indicates that an event or situation resulted in people being injured but not killed.
-
D.
combatantLeaderKilledOrMortallyWounded
Indicates that the leader of a combatant force was killed outright or suffered wounds that were fatal in the context of the conflict or engagement.
-
E.
actedDespiteWounds
Indicates that an entity performed an action or fulfilled a role even though it was wounded or injured at the time.
- 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_69ee5b44391c81908bdbd8813ba9aa99 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f60c4039548190a47fb89a3a393b70 |
completed | May 2, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69f5b0021da88190bdd4cf2698c23edf |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:33 p.m.