Triple
T8943822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Josef Hoffmann |
E212969
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Hoffmann |
E757065
|
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: Hoffmann | Statement: [Josef Hoffmann, familyName, Hoffmann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hoffmann Context triple: [Josef Hoffmann, familyName, Hoffmann]
-
A.
Hoffmann
chosen
Hoffmann is a common German surname borne by numerous notable figures in fields such as science, literature, music, and politics.
-
B.
E. T. A. Hoffmann
E. T. A. Hoffmann was a German Romantic author, composer, and jurist best known for his fantastical and often macabre tales that influenced writers like Edgar Allan Poe and inspired works such as Tchaikovsky’s ballet "The Nutcracker."
-
C.
Heinrich Hoffmann
Heinrich Hoffmann was Adolf Hitler’s personal photographer and a prominent Nazi-era photographer and publisher whose studio employed Eva Braun.
-
D.
Hoffmann und Campe
Hoffmann und Campe is a historic German publishing house, best known for issuing major 19th-century literary works, including those of Heinrich Heine.
-
E.
Hoffman
Hoffman is a common German-origin surname borne by numerous notable individuals across fields such as business, entertainment, science, and politics.
- 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_69ca839694c88190b324ffeb43d23b08 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66da71808190b4454b2f95aae0bd |
completed | April 1, 2026, 12:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc1f87db481909d40ed6fb0a4c8c9 |
completed | April 3, 2026, 1:34 p.m. |
Created at: March 30, 2026, 6:58 p.m.