Triple
T2878085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martin Bormann |
E56926
|
entity |
| Predicate | previousConviction |
P6201
|
FINISHED |
| Object | 1924 conviction for complicity in murder of Walther Kadow |
—
|
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: 1924 conviction for complicity in murder of Walther Kadow | Statement: [Martin Bormann, previousConviction, 1924 conviction for complicity in murder of Walther Kadow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousConviction Context triple: [Martin Bormann, previousConviction, 1924 conviction for complicity in murder of Walther Kadow]
-
A.
convictedOf
chosen
Indicates that a person or entity has been found guilty of committing a specified offense or crime through a formal legal process.
-
B.
hasFirstConviction
Indicates that an entity has received its first legal conviction for an offense.
-
C.
numberOfConvictions
Indicates the count of times an entity has been formally found guilty of an offense.
-
D.
dateOfConviction
Indicates the specific calendar date on which a person or entity was formally found guilty of an offense.
-
E.
convictionStatusInOriginalTrial
Indicates whether an entity was found guilty or not guilty in the initial (original) court trial.
- 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_69ab4a4ced288190ab6d3e062d10f7f6 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abe008925c81909683d0ebc6227e5e |
completed | March 7, 2026, 8:21 a.m. |
| PD | Predicate disambiguation | batch_69abdd142e4c8190b424cb0c5ff40d04 |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:03 p.m.