Triple

T20555774
Position Surface form Disambiguated ID Type / Status
Subject Günther Behnisch E504715 entity
Predicate child P120 FINISHED
Object Stefan Behnisch
Stefan Behnisch is a German architect known for his sustainable and human-centered designs and as the principal of the firm Behnisch Architekten.
E1439015 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: Stefan Behnisch | Statement: [Günther Behnisch, child, Stefan Behnisch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stefan Behnisch
Context triple: [Günther Behnisch, child, Stefan Behnisch]
  • A. Dietmar Roth
    Dietmar Roth is a modern biblical scholar known for producing a contemporary reconstruction of Marcion’s Gospel.
  • B. Uwe Schlaich
    Uwe Schlaich is a German architect known for designing the main building of the Topography of Terror documentation center in Berlin.
  • C. Jürgen Mayer
    Jürgen Mayer is a German architect and artist known for his innovative, sculptural designs that blend architecture with digital technology and public art.
  • D. Andreas Schlüter
    Andreas Schlüter is a German local politician who serves as the mayor of the municipality of Gerswalde in Brandenburg.
  • E. Andreas Schlüter
    Andreas Schlüter was a prominent German Baroque sculptor and architect best known for his influential work in Prussia at the turn of the 18th century.
  • 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: Stefan Behnisch
Triple: [Günther Behnisch, child, Stefan Behnisch]
Generated description
Stefan Behnisch is a German architect known for his sustainable and human-centered designs and as the principal of the firm Behnisch Architekten.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Stefan Behnisch
Target entity description: Stefan Behnisch is a German architect known for his sustainable and human-centered designs and as the principal of the firm Behnisch Architekten.
  • A. Dietmar Roth
    Dietmar Roth is a modern biblical scholar known for producing a contemporary reconstruction of Marcion’s Gospel.
  • B. Uwe Schlaich
    Uwe Schlaich is a German architect known for designing the main building of the Topography of Terror documentation center in Berlin.
  • C. Jürgen Mayer
    Jürgen Mayer is a German architect and artist known for his innovative, sculptural designs that blend architecture with digital technology and public art.
  • D. Andreas Schlüter
    Andreas Schlüter was a prominent German Baroque sculptor and architect best known for his influential work in Prussia at the turn of the 18th century.
  • E. Andreas Schlüter
    Andreas Schlüter is a German local politician who serves as the mayor of the municipality of Gerswalde in Brandenburg.
  • 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_69e0b4b52c048190952b4d0f430813a3 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a5dd02588190abddfcb868259a38 completed April 20, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08acd907088190b1c261267381c3b8 completed May 16, 2026, 5:43 p.m.
NEDg Description generation batch_6a08ae5320d08190b8ce6fbe4909af18 completed May 16, 2026, 5:50 p.m.
NED2 Entity disambiguation (via description) batch_6a08aed4a9908190bf7bd5f0147ff6f2 completed May 16, 2026, 5:52 p.m.
Created at: April 16, 2026, 11:38 a.m.