Triple
T3235905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Adrianople (378) |
E67853
|
entity |
| Predicate | casualtiesRoman |
P10775
|
FINISHED |
| Object | very high |
—
|
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: very high | Statement: [Battle of Adrianople (378), casualtiesRoman, very high]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: casualtiesRoman Context triple: [Battle of Adrianople (378), casualtiesRoman, very high]
-
A.
casualties
Indicates that an event, action, or situation resulted in people being killed or injured.
-
B.
casualtiesDescription
chosen
Indicates a textual description of the human losses (such as deaths, injuries, or missing persons) resulting from an event or incident.
-
C.
estimatedRomanForces
Indicates that a specified quantity represents an estimate of the size or strength of Roman military forces involved in a particular context or event.
-
D.
casualtiesAssociatedWithEvent
Indicates that certain casualties (deaths or injuries) are linked to, or resulted from, a specific event.
-
E.
casualtiesIncluded
Indicates that the referenced count or report of casualties explicitly includes the specified individuals or groups.
- 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_69ad858d27348190abb61c280b4c86a9 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaee05d34819095dbce4db6ac8613 |
completed | March 8, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69ada4159e0481908cbbdd750f5e08c7 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:08 p.m.