Triple
T3628355
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | murder of Jean-Paul Marat |
E76893
|
entity |
| Predicate | hasPerpetratorStatement |
P49639
|
FINISHED |
| Object | I killed one man to save a hundred thousand |
—
|
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: I killed one man to save a hundred thousand | Statement: [murder of Jean-Paul Marat, hasPerpetratorStatement, I killed one man to save a hundred thousand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPerpetratorStatement Context triple: [murder of Jean-Paul Marat, hasPerpetratorStatement, I killed one man to save a hundred thousand]
-
A.
hasAccuser
Indicates that one entity serves as the accuser of another entity in a dispute, complaint, or allegation.
-
B.
hasPerpetratorOccupation
Indicates that the occupation or job role of the perpetrator involved in an act or incident is being specified.
-
C.
perpetratedBy
Indicates that an action, event, or wrongdoing was carried out or caused by a particular agent or entity.
-
D.
suspectedPerpetrator
Indicates that an entity is believed or alleged to be the person responsible for committing a particular harmful or illegal act.
-
E.
guiltyOf
Indicates that an entity has been judged or determined to have committed a particular offense, crime, or wrongful act.
- F. None of above. chosen
Provenance (4 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_69ad85dc03948190b35b7189e4175bcc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc2df2b708190afef6925a53ec551 |
completed | March 8, 2026, 6:41 p.m. |
| PD | Predicate disambiguation | batch_69adb8410a5881909c94818d7060b2b0 |
completed | March 8, 2026, 5:56 p.m. |
| PDg | Predicate description generation | batch_69adb902e61c81908f10494f828e260f |
completed | March 8, 2026, 5:59 p.m. |
Created at: March 8, 2026, 3:23 p.m.