Triple
T36101126
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hendrik Höfgen |
E1044207
|
entity |
| Predicate | relationshipToRegime |
P20515
|
FINISHED |
| Object | collaborator |
—
|
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: collaborator | Statement: [Hendrik Höfgen, relationshipToRegime, collaborator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToRegime Context triple: [Hendrik Höfgen, relationshipToRegime, collaborator]
-
A.
associatedWithRegime
chosen
Indicates a relationship where an entity is linked or connected to a particular regime, such as a political, governmental, or ruling system.
-
B.
associatedWithRegimeChange
Indicates a relationship in which an entity is involved in, linked to, or plays a role in bringing about a change in political regime or leadership.
-
C.
relationshipToNationalGovernment
Indicates the nature or type of connection an entity has with a national-level government.
-
D.
politicalRegimeContext
Indicates the type of political regime or governing system within which an action, event, or relationship takes place.
-
E.
regimeCharacterizedAs
Indicates that a political or governance regime is described or classified as having a particular character, quality, or type.
- 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_69f76e338e2c8190b7f3bc68bec76349 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0895b48190acdd88dc10db7be7 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:08 p.m.