Triple
T30440433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soham murders |
E774424
|
entity |
| Predicate | coAccusedSentence |
P170222
|
FINISHED |
| Object | 3.5 years imprisonment |
—
|
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: 3.5 years imprisonment | Statement: [Soham murders, coAccusedSentence, 3.5 years imprisonment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coAccusedSentence Context triple: [Soham murders, coAccusedSentence, 3.5 years imprisonment]
-
A.
accusedOf
Indicates that one entity has formally alleged or claimed that another entity committed a specific wrongdoing or offense.
-
B.
coAccusedVerdict
chosen
Indicates that two or more individuals who were jointly accused in a case received a particular verdict or outcome together.
-
C.
accusedIn
Indicates that a person or entity is formally charged with wrongdoing in a particular case, proceeding, or context.
-
D.
accusedText
Indicates that one entity has formally alleged or charged another entity with wrongdoing or an offense in written or textual form.
-
E.
coAccusedInCaseWith
Indicates that two or more entities are jointly accused as defendants in the same legal case.
- 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_69f68f670b608190a0b6ab60d722b4e0 |
completed | May 2, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69f68b7b03488190b1db5fde4c7dd6e5 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 8:08 p.m.