Triple

T391185
Position Surface form Disambiguated ID Type / Status
Subject Berlin Botanical Garden E8883 entity
Predicate architect P184 FINISHED
Object Alfred Koerner
Alfred Koerner was an architect known for his work on the Berlin Botanical Garden.
 E56420 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: Alfred Koerner | Statement: [Berlin Botanical Garden, architect, Alfred Koerner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Alfred Koerner
Context triple: [Berlin Botanical Garden, architect, Alfred Koerner]
  • A. Eduard Meyer
    Eduard Meyer was a prominent German historian and classical scholar known for his influential works on ancient history and historiography.
  • B. Eberhard Schöngarth
    Eberhard Schöngarth was a high-ranking Nazi SS and police leader involved in war crimes and the Holocaust, including participation in the Wannsee Conference.
  • C. Paul Körner
    Paul Körner was a high-ranking Nazi official and close associate of Hermann Göring who played a key role in the economic and industrial mobilization of the Third Reich.
  • D. Gustav Riebmann
    Gustav Riebmann is a fictional character from the American prime-time soap opera "Falcon Crest," known for being a powerful and manipulative antagonist.
  • E. Wilhelm Siegling
    Wilhelm Siegling was a German linguist and philologist known for his pioneering work on the Tocharian languages and their classification within the Indo-European language family.
  • 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: Alfred Koerner
Triple: [Berlin Botanical Garden, architect, Alfred Koerner]
Generated description
Alfred Koerner was an architect known for his work on the Berlin Botanical Garden.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Alfred Koerner
Target entity description: Alfred Koerner was an architect known for his work on the Berlin Botanical Garden.
  • A. Eduard Meyer
    Eduard Meyer was a prominent German historian and classical scholar known for his influential works on ancient history and historiography.
  • B. Eberhard Schöngarth
    Eberhard Schöngarth was a high-ranking Nazi SS and police leader involved in war crimes and the Holocaust, including participation in the Wannsee Conference.
  • C. Paul Körner
    Paul Körner was a high-ranking Nazi official and close associate of Hermann Göring who played a key role in the economic and industrial mobilization of the Third Reich.
  • D. Gustav Riebmann
    Gustav Riebmann is a fictional character from the American prime-time soap opera "Falcon Crest," known for being a powerful and manipulative antagonist.
  • E. Wilhelm Siegling
    Wilhelm Siegling was a German linguist and philologist known for his pioneering work on the Tocharian languages and their classification within the Indo-European language family.
  • 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_69a2e7f55c60819097aff65ea2ca2832 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec5d73e881909101308a583c8f13 completed Feb. 28, 2026, 1:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69a447f8fac481909c4848ca9b789bc3 completed March 1, 2026, 2:06 p.m.
NEDg Description generation batch_69a448719fd881909c183132bb98898b completed March 1, 2026, 2:08 p.m.
NED2 Entity disambiguation (via description) batch_69a448c743388190807694111ad63678 completed March 1, 2026, 2:10 p.m.
Created at: Feb. 28, 2026, 1:08 p.m.