Triple
T7709814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Abensberg |
E174718
|
entity |
| Predicate | AustrianGunsLost |
P78274
|
FINISHED |
| Object | about 12 guns |
—
|
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 12 guns | Statement: [Battle of Abensberg, AustrianGunsLost, about 12 guns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AustrianGunsLost Context triple: [Battle of Abensberg, AustrianGunsLost, about 12 guns]
-
A.
AustrianGunsCaptured
Indicates that guns belonging to Austrian forces were seized and taken by another party.
-
B.
AustrianCasualtiesApprox
Indicates an approximate number or estimate of casualties suffered by Austrian forces or entities.
-
C.
AustrianArmy
Indicates that an entity is the Austrian Army or is serving as part of the Austrian Army in a given context.
-
D.
combatantCommanderAustria
Indicates that the referenced entity served as a military commander for Austria in a particular conflict or combat situation.
-
E.
involvedUnitAustriaHungary
Indicates that the unit or force specified was involved on behalf of Austria-Hungary in the referenced event or conflict.
- 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_69c6995b3e8c8190833108f883d5f53c |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c702ebb7448190ae8d47fe0cbb0907 |
completed | March 27, 2026, 10:21 p.m. |
| PD | Predicate disambiguation | batch_69c701683dec8190be9861e592aa8ce0 |
completed | March 27, 2026, 10:15 p.m. |
| PDg | Predicate description generation | batch_69c702e9a32081909a153190a62af426 |
completed | March 27, 2026, 10:21 p.m. |
Created at: March 27, 2026, 4:04 p.m.