Triple
T21579190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lorenz Adlon |
E532478
|
entity |
| Predicate | hasNameInLanguage |
P15
|
FINISHED |
| Object | Lorenz Adlon@de |
E532478
|
NE 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: Lorenz Adlon@de | Statement: [Lorenz Adlon, hasNameInLanguage, Lorenz Adlon@de]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lorenz Adlon@de Context triple: [Lorenz Adlon, hasNameInLanguage, Lorenz Adlon@de]
-
A.
Lorenz Adlon
chosen
Lorenz Adlon was a prominent German restaurateur and hotelier best known for creating Berlin’s legendary luxury Hotel Adlon in the early 20th century.
-
B.
Markus Lanz
Markus Lanz is a German television presenter and journalist best known for hosting major talk and entertainment shows on German public television.
-
C.
Max Adrian
Max Adrian was a British character actor known for his work on stage with the Old Vic and in films and television, often appearing in period dramas and literary adaptations.
-
D.
Eric Ladin
Eric Ladin is an American actor known for his roles in television series such as "Generation Kill," "The Killing," and "Boardwalk Empire."
-
E.
Lukas Ettlin
Lukas Ettlin is a Swiss-born cinematographer and director known for his work on feature films and television series, including action and genre projects.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69e0c4618bec8190bcb0feb74568cbb1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eeeb5ac1048190aa45d7d3c780b5c9 |
completed | April 27, 2026, 4:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09f67889bc81908d640cbe0bc4b121 |
completed | May 17, 2026, 5:10 p.m. |
Created at: April 16, 2026, 6:31 p.m.