Triple
T23910719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heinrich Himmler (as adjutant) |
E601930
|
entity |
| Predicate | contextOfRole |
P2919
|
FINISHED |
| Object | Nazi Germany |
—
|
NE NERFINISHED |
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: Nazi Germany | Statement: [Heinrich Himmler (as adjutant), contextOfRole, Nazi Germany]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contextOfRole Context triple: [Heinrich Himmler (as adjutant), contextOfRole, Nazi Germany]
-
A.
contextOf
chosen
Indicates that one entity provides the situational, informational, or environmental background within which another entity exists, occurs, or is interpreted.
-
B.
narrativeRoleContext
Indicates the contextual narrative function or role an entity plays within a story or discourse (e.g., protagonist, antagonist, narrator) relative to other elements.
-
C.
contingencyRole
Indicates a role that an entity assumes specifically in the context of a contingent, conditional, or dependent situation or relationship.
-
D.
roleInScene
Indicates that an entity participates in a particular scene with a specific role or function within that scene.
-
E.
roleInText
Indicates that an entity participates in a text with a specific function or capacity (e.g., author, editor, character).
- 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_69e2953a187081908346a9f36e85fc98 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1ce94f65c8190807723344fa0b837 |
completed | April 29, 2026, 9:25 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:38 p.m.