Triple
T30440417
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soham murders |
E774424
|
entity |
| Predicate | occupationOfPerpetrator |
P29064
|
FINISHED |
| Object | school caretaker |
—
|
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: school caretaker | Statement: [Soham murders, occupationOfPerpetrator, school caretaker]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occupationOfPerpetrator Context triple: [Soham murders, occupationOfPerpetrator, school caretaker]
-
A.
hasPerpetratorOccupation
chosen
Indicates that the occupation or job role of the perpetrator involved in an act or incident is being specified.
-
B.
perpetratorType
Indicates the classification or category of the entity that carried out or is responsible for a harmful, illegal, or otherwise wrongful act.
-
C.
roleInCrime
Indicates the specific function, responsibility, or participation an entity has within the commission of a particular crime.
-
D.
perpetratorStatus
Indicates the role or condition of an individual in relation to committing or being responsible for a specific harmful or criminal act.
-
E.
governmentTypeOfPerpetrator
Indicates the form of government under which the perpetrator operated or was affiliated when carrying out the action or offense.
- 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_69f22493ef9c8190ae8c2afcb7f994c8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6a0ea04888190ac3a813b603bcb5c |
completed | May 3, 2026, 1:12 a.m. |
| PD | Predicate disambiguation | batch_69f69fe463248190aa78128abeab1183 |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 29, 2026, 8:08 p.m.