Triple
T37138691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johann Radmann |
E920043
|
entity |
| Predicate | focusOfInvestigations |
P59454
|
FINISHED |
| Object | Auschwitz crimes |
—
|
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: Auschwitz crimes | Statement: [Johann Radmann, focusOfInvestigations, Auschwitz crimes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusOfInvestigations Context triple: [Johann Radmann, focusOfInvestigations, Auschwitz crimes]
-
A.
investigativeFocus
chosen
Indicates that an entity is the primary subject or target of investigation, inquiry, or detailed scrutiny by another entity.
-
B.
investigatesIn
Indicates that an entity conducts an investigation or inquiry within, or focused on, a particular context, location, or domain.
-
C.
asksToInvestigate
Indicates that one entity requests another entity to carry out an investigation into something.
-
D.
investigatesAt
Indicates that an entity conducts an investigation or research activity at a specific location or institution.
-
E.
containsInvestigationOf
Indicates that one entity includes or encompasses an investigation or inquiry concerning 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_69f76e9e9d008190a250b0387c992c74 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd4f39b5008190b83b3227ce22c509 |
completed | May 8, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69fd4df17c548190a4e2a6fea70f7e10 |
completed | May 8, 2026, 2:44 a.m. |
Created at: May 3, 2026, 4:15 p.m.