Triple
T9103605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Lodi |
E218418
|
entity |
| Predicate | AustrianCasualtiesApproximate |
P22214
|
FINISHED |
| Object | around 2,000 killed and 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: around 2,000 killed and wounded | Statement: [Battle of Lodi, AustrianCasualtiesApproximate, around 2,000 killed and wounded]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AustrianCasualtiesApproximate Context triple: [Battle of Lodi, AustrianCasualtiesApproximate, around 2,000 killed and wounded]
-
A.
AustrianCasualtiesApprox
chosen
Indicates an approximate number or estimate of casualties suffered by Austrian forces or entities.
-
B.
AustrianArmy
Indicates that an entity is the Austrian Army or is serving as part of the Austrian Army in a given context.
-
C.
AustrianGunsLost
Indicates that certain guns or artillery pieces belonging to Austrian forces were lost.
-
D.
combatantStrengthAustrianSide
Indicates that the associated entity represents the strength or size of the Austrian side’s combatant forces in a conflict.
-
E.
combatantCommanderAustria
Indicates that the referenced entity served as a military commander for Austria in a particular conflict or combat situation.
- 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_69ca83db7448819090d0a5de842ef2ac |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca56f1f10819091abadf7cd06c3a6 |
completed | April 1, 2026, 4:56 a.m. |
| PD | Predicate disambiguation | batch_69cc65fc7f408190a5846e29ab3b97e5 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:15 p.m.