Triple

T13096013
Position Surface form Disambiguated ID Type / Status
Subject Hermann Höfle E310590 entity
Predicate familyName P18 FINISHED
Object Höfle
Höfle is a German-language surname most notably associated with SS officer Hermann Höfle, a key organizer of the Holocaust’s Operation Reinhard.
E1019744 NE FINISHED

How this triple was built (4 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: Höfle | Statement: [Hermann Höfle, familyName, Höfle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Höfle
Context triple: [Hermann Höfle, familyName, Höfle]
  • A. Waltershof
    Waltershof is an industrial and port district of Hamburg, Germany, located within the borough of Hamburg-Mitte.
  • B. Baltschieder
    Baltschieder is a small Swiss municipality in the canton of Valais, located in the Upper Valais region of the Alps.
  • C. Pfaffstätten
    Pfaffstätten is a market town in Lower Austria known for its wine-growing tradition and location within the Baden district near Vienna.
  • D. Hohenwart
    Hohenwart is a small municipality in Bavaria, Germany, known for its rural character and location within the Upper Bavarian region.
  • E. Gersthofen
    Gersthofen is a town in Bavaria, Germany, located just north of Augsburg and known for its industrial presence and role as a regional transport hub.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Höfle
Triple: [Hermann Höfle, familyName, Höfle]
Generated description
Höfle is a German-language surname most notably associated with SS officer Hermann Höfle, a key organizer of the Holocaust’s Operation Reinhard.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Höfle
Target entity description: Höfle is a German-language surname most notably associated with SS officer Hermann Höfle, a key organizer of the Holocaust’s Operation Reinhard.
  • A. Waltershof
    Waltershof is an industrial and port district of Hamburg, Germany, located within the borough of Hamburg-Mitte.
  • B. Baltschieder
    Baltschieder is a small Swiss municipality in the canton of Valais, located in the Upper Valais region of the Alps.
  • C. Pfaffstätten
    Pfaffstätten is a market town in Lower Austria known for its wine-growing tradition and location within the Baden district near Vienna.
  • D. Hohenwart
    Hohenwart is a small municipality in Bavaria, Germany, known for its rural character and location within the Upper Bavarian region.
  • E. Gersthofen
    Gersthofen is a town in Bavaria, Germany, located just north of Augsburg and known for its industrial presence and role as a regional transport hub.
  • F. None of above. chosen

Provenance (5 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_69d806a733548190989cfd4ce981ca33 completed April 9, 2026, 8:05 p.m.
NER Named-entity recognition batch_69d9814e88a0819088418c792ce7aa57 completed April 10, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6d619b82c819093d0d98db88eb9ae completed May 3, 2026, 4:59 a.m.
NEDg Description generation batch_69f6d7da15b08190ba181bbb1a386acb completed May 3, 2026, 5:06 a.m.
NED2 Entity disambiguation (via description) batch_69f6d8cdf48081909b6088e7d72fc3c5 completed May 3, 2026, 5:10 a.m.
Created at: April 9, 2026, 9:03 p.m.