Triple
T14992441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herbert Backe |
E373869
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Backe |
E373869
|
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: Backe | Statement: [Herbert Backe, familyName, Backe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Backe Context triple: [Herbert Backe, familyName, Backe]
-
A.
Backe
chosen
Backe is a German surname most notably associated with Herbert Backe, a Nazi-era politician and agricultural minister.
-
B.
Badeloch
Badeloch is a central female character in Joost van den Vondel’s Dutch play "Gijsbrecht van Aemstel," known as the loyal and tragic wife of the title hero.
-
C.
Mahlberg
Mahlberg is a small town and municipality in the Ortenau district of Baden-Württemberg in southwestern Germany.
-
D.
Wiedensahl
Wiedensahl is a small village in Lower Saxony, Germany, best known as the birthplace of the humorist and illustrator Wilhelm Busch.
-
E.
Bakoven
Bakoven is a small, picturesque seaside suburb of Cape Town, South Africa, known for its rocky coves, sheltered beaches, and views of the Atlantic Ocean and Twelve Apostles.
- 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_69d85ccc84388190aa151e5173370c8d |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded715db408190b44e8a8452c79764 |
completed | April 15, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe969842848190a030db797c851fed |
completed | May 9, 2026, 2:06 a.m. |
Created at: April 10, 2026, 2:53 a.m.