Triple
T37172558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Telavåg |
E920952
|
entity |
| Predicate | governingCountryDuringWar |
P203235
|
FINISHED |
| Object | occupied Norway under German control |
—
|
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: occupied Norway under German control | Statement: [Telavåg, governingCountryDuringWar, occupied Norway under German control]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governingCountryDuringWar Context triple: [Telavåg, governingCountryDuringWar, occupied Norway under German control]
-
A.
countryDuringWar
Indicates that a country exists or participates as a relevant actor during a specified war or armed conflict.
-
B.
governedDuringWarBy
chosen
Indicates that an entity was under the authority or control of another entity specifically during a period of war.
-
C.
countryGovernedDuringConflict
Indicates that a country was governed or administered by a particular authority or regime during a specified conflict or war.
-
D.
countryForWhichFought
Indicates the country on whose behalf or under whose authority an entity participated in a conflict or war.
-
E.
countryDuringBattle
Indicates that a specified country was involved in or existed as a relevant participant or context during a particular battle.
- 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_69f76ea16f288190b445aa1604d996f4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a033029023481909d9fa4a76b954879 |
completed | May 12, 2026, 1:50 p.m. |
| PD | Predicate disambiguation | batch_6a032d9f1fa48190bd1c94a8f930d02c |
completed | May 12, 2026, 1:39 p.m. |
Created at: May 3, 2026, 4:15 p.m.