Triple
T13355757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nehring |
E318686
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Walther Nehring |
—
|
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: Walther Nehring | Statement: [Nehring, hasNotableBearer, Walther Nehring]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Walther Nehring Context triple: [Nehring, hasNotableBearer, Walther Nehring]
-
A.
Walther Nehring
chosen
Walther Nehring was a German general and panzer commander in World War II, known for leading armored formations on the Eastern Front and in North Africa.
-
B.
Adolf Borchers
Adolf Borchers was a German Luftwaffe fighter ace of World War II, credited with numerous aerial victories on the Eastern Front.
-
C.
Walther Kranz
Walther Kranz was a German classical philologist and historian of ancient philosophy best known for co-editing the standard collection of Presocratic fragments commonly cited as Diels–Kranz.
-
D.
Walter Röhrig
Walter Röhrig was a German art director and production designer best known for his influential work on early Expressionist cinema.
-
E.
Walther Sommerlath
Walther Sommerlath was a German businessman best known as the father of Queen Silvia of Sweden.
- 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_69d806b7bbac8190b85278c87fa7aff3 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99f1ef94c81909a59b7c3f77d3335 |
completed | April 11, 2026, 1:08 a.m. |
Created at: April 9, 2026, 9:32 p.m.