Triple
T19092164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roland Møller |
E467313
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Møller |
—
|
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: Møller | Statement: [Roland Møller, familyName, Møller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Møller Context triple: [Roland Møller, familyName, Møller]
-
A.
Møller
chosen
Møller is a Danish surname most prominently associated with the shipping magnate Mærsk Mc-Kinney Møller and the A.P. Moller–Maersk business dynasty.
-
B.
Malchow-Møller
Malchow-Møller is the surname of Danish economist and academic leader Nikolaj Malchow-Møller.
-
C.
Mogens
Mogens is a Danish masculine given name commonly used in Denmark and other Scandinavian countries.
-
D.
Per Möller Jensen
Per Möller Jensen is a Danish drummer best known for his work with the Swedish metal band The Haunted and previously with Artillery.
-
E.
Hugo Lous Mohr
Hugo Lous Mohr was a Norwegian painter best known for his monumental church decorations and religious artworks in the early to mid-20th century.
- 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e34c22a08190bf34f92f727268c5 |
completed | April 20, 2026, 8:26 a.m. |
Created at: April 10, 2026, 12:04 p.m.