Triple
T23977226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Josef Terboven |
E604402
|
entity |
| Predicate | countryOfOccupationAdministration |
P38493
|
FINISHED |
| Object | Norway |
—
|
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: Norway | Statement: [Josef Terboven, countryOfOccupationAdministration, Norway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryOfOccupationAdministration Context triple: [Josef Terboven, countryOfOccupationAdministration, Norway]
-
A.
countryOfOffice
chosen
Indicates the country in which a person’s official position, role, or office is held or exercised.
-
B.
countryAdministeredNowPartOf
Indicates that a country currently administers a territory or region that is now considered part of another country.
-
C.
administrativeTerritorialEntityOf
Indicates that one entity serves as the administrative territorial unit or jurisdiction to which another entity belongs or is governed by.
-
D.
countryGovernedOnBehalfOf
Indicates that a country is administered or ruled by one party acting in the name or interest of another party.
-
E.
isCentralAdministrativeBodyOf
Indicates that one entity serves as the main governing or coordinating administrative authority for another entity or system.
- 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_69e29543f40c819087700b7a272afb60 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d2bad6ec81908b5649223a72c2b9 |
completed | April 29, 2026, 9:43 a.m. |
| PD | Predicate disambiguation | batch_69f161578d54819084a8b35496299993 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:26 p.m.