Triple
T32965983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thraustila |
E843367
|
entity |
| Predicate | deathOfVictim |
P33482
|
FINISHED |
| Object | Valentinian III |
—
|
NE NERFINISHED |
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: Valentinian III | Statement: [Thraustila, deathOfVictim, Valentinian III]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deathOfVictim Context triple: [Thraustila, deathOfVictim, Valentinian III]
-
A.
murderVictimOf
chosen
Indicates that one entity is the person who was killed by another entity in an act of murder.
-
B.
hasMannerOfDeathOfVictim
Indicates the specific way or circumstances in which the victim died in relation to the event or action being described.
-
C.
victimDiedIn
Indicates that the victim lost their life as a result of, or during the course of, the referenced event or circumstance.
-
D.
victimWas
Indicates that one entity was the victim of an action, event, or harmful behavior carried out by another entity.
-
E.
deathBy
Indicates a relationship where one entity’s death is caused by another entity, event, or factor.
- 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_69f3494af2808190ad98cec2f1bc0fe6 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f73ae120bc8190bff94d38d7a7a00d |
completed | May 3, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69f73a38d0848190aa5139144b8561c6 |
completed | May 3, 2026, 12:06 p.m. |
Created at: May 1, 2026, 1:21 a.m.