Triple
T29796876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Noreia |
E756576
|
entity |
| Predicate | RomanLosses |
P165220
|
FINISHED |
| Object | heavy casualties |
—
|
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: heavy casualties | Statement: [Battle of Noreia, RomanLosses, heavy casualties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: RomanLosses Context triple: [Battle of Noreia, RomanLosses, heavy casualties]
-
A.
CarthaginianLosses
Indicates the number or extent of losses suffered by the Carthaginians in a given conflict or event.
-
B.
casualtiesSideRomanEmpire
chosen
Indicates that the recorded casualties in a conflict or battle occurred on the side of the Roman Empire.
-
C.
RomanLegionsDestroyed
Indicates that one or more Roman legions were annihilated or decisively defeated, typically resulting in their destruction as effective military units.
-
D.
ItalianLosses
Indicates that the relationship concerns losses (such as casualties, equipment, or territory) incurred by Italian forces or entities.
-
E.
GermanLoss
Indicates that Germany experiences a loss, defeat, or negative outcome in the specified context or event.
- 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_69f22454583081908927516cb9938d1d |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 5:15 p.m.