Triple
T17880320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johannsen |
E447065
|
entity |
| Predicate | hasCognate |
P2525
|
FINISHED |
| Object | Johansen |
—
|
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: Johansen | Statement: [Johannsen, hasCognate, Johansen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Johansen Context triple: [Johannsen, hasCognate, Johansen]
-
A.
Johansen
chosen
Johansen is a surname of Scandinavian origin commonly found in Norway and Denmark.
-
B.
Jens
Jens is a masculine given name commonly used in Scandinavian and German-speaking countries, equivalent to "John" in English.
-
C.
Jens
Jens is a small municipality in the canton of Bern in Switzerland, located within the bilingual region around the city of Biel/Bienne.
-
D.
Johnsen
Johnsen is a surname of Scandinavian origin, commonly used as a patronymic family name meaning "son of John."
-
E.
Aas-Jakobsen
Aas-Jakobsen is a Norwegian consulting engineering firm renowned for its expertise in designing major bridges and other large-scale infrastructure projects.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49c0e56bc819097649377b520de63 |
completed | April 19, 2026, 9:10 a.m. |
Created at: April 10, 2026, 10:18 a.m.