Triple
T9054959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Murder of Geta |
E216973
|
entity |
| Predicate | hasPerpetratorRole |
P60350
|
FINISHED |
| Object | Roman co-emperor |
—
|
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: Roman co-emperor | Statement: [Murder of Geta, hasPerpetratorRole, Roman co-emperor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPerpetratorRole Context triple: [Murder of Geta, hasPerpetratorRole, Roman co-emperor]
-
A.
hasPerpetrators
Indicates that certain entities are responsible for carrying out, committing, or executing a particular act, event, or wrongdoing.
-
B.
hasPerpetratorStatement
Indicates that a statement has been made by the perpetrator regarding the related event or action.
-
C.
hasPerpetratorOrigin
Indicates that the origin or source of a perpetrator (such as their nationality, place of birth, or background) is associated with a particular event, action, or crime.
-
D.
perpetratorStatus
chosen
Indicates the role or condition of an individual in relation to committing or being responsible for a specific harmful or criminal act.
-
E.
hasAccusedRole
Indicates that one entity has the role or capacity of making an accusation against another entity.
- 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_69ca83d4425481909a319dab847724ec |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc7a7488188190b3dd6bc2f2377503 |
completed | April 1, 2026, 1:52 a.m. |
| PD | Predicate disambiguation | batch_69cc5ee6d83c819095d8ed0779aa8511 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:10 p.m.