Triple
T27533656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alizon Device |
E695038
|
entity |
| Predicate | causeOfAccusation |
P126264
|
FINISHED |
| Object | alleged bewitching of John Law |
—
|
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: alleged bewitching of John Law | Statement: [Alizon Device, causeOfAccusation, alleged bewitching of John Law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: causeOfAccusation Context triple: [Alizon Device, causeOfAccusation, alleged bewitching of John Law]
-
A.
accusationType
Indicates the specific category or nature of an accusation made by one party against another.
-
B.
victimOfAccusation
Indicates that an entity is the target or subject of an accusation made by another party.
-
C.
accusationDescription
chosen
Indicates that a statement or explanation is being provided that details the nature, content, or specifics of an accusation made by one party against another.
-
D.
crimeAccusation
Indicates that one entity formally accuses another entity of having committed a crime.
-
E.
resultOfAccusation
Indicates that one entity is the outcome, consequence, or product of an accusation made by 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_69ef538608b081908b9f659bb09d5e0f |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 27, 2026, 1:27 p.m.