Triple

T18265662
Position Surface form Disambiguated ID Type / Status
Subject Schloss Salem E437476 entity
Predicate founder P104 FINISHED
Object Gunthram von Adelsreute
Gunthram von Adelsreute was a medieval nobleman credited with establishing the estate that later became known as Schloss Salem in southern Germany.
 E1315947 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: Gunthram von Adelsreute | Statement: [Schloss Salem, founder, Gunthram von Adelsreute]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gunthram von Adelsreute
Context triple: [Schloss Salem, founder, Gunthram von Adelsreute]
  • A. Herzog von Berg
    Herzog von Berg is the German title historically used for the dukes who ruled the Duchy of Berg in the Holy Roman Empire.
  • B. Helmbrechts
    Helmbrechts is a small town in northern Bavaria, Germany, known for its textile industry and location in the Franconian Forest region.
  • C. Hünfeld
    Hünfeld is a small town in the state of Hesse in central Germany, known in part for its association with computing pioneer Konrad Zuse.
  • D. Ingenried
    Ingenried is a small rural municipality in the Weilheim-Schongau district of Bavaria in southern Germany.
  • E. Prince of Essling
    Prince of Essling is a French noble title created by Napoleon I for Marshal André Masséna in recognition of his military achievements.
  • 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: Gunthram von Adelsreute
Triple: [Schloss Salem, founder, Gunthram von Adelsreute]
Generated description
Gunthram von Adelsreute was a medieval nobleman credited with establishing the estate that later became known as Schloss Salem in southern Germany.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gunthram von Adelsreute
Target entity description: Gunthram von Adelsreute was a medieval nobleman credited with establishing the estate that later became known as Schloss Salem in southern Germany.
  • A. Herzog von Berg
    Herzog von Berg is the German title historically used for the dukes who ruled the Duchy of Berg in the Holy Roman Empire.
  • B. Helmbrechts
    Helmbrechts is a small town in northern Bavaria, Germany, known for its textile industry and location in the Franconian Forest region.
  • C. Hünfeld
    Hünfeld is a small town in the state of Hesse in central Germany, known in part for its association with computing pioneer Konrad Zuse.
  • D. Ingenried
    Ingenried is a small rural municipality in the Weilheim-Schongau district of Bavaria in southern Germany.
  • E. Prince of Essling
    Prince of Essling is a French noble title created by Napoleon I for Marshal André Masséna in recognition of his military achievements.
  • 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_69d8b913351c8190932b6a426de04b41 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ff79851481909a4bbeb14fb00647 completed April 19, 2026, 4:14 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03b3f6c1b081908fdd0ccb6f1bf633 completed May 12, 2026, 11:12 p.m.
NEDg Description generation batch_6a03b4f0cd188190a9577a3999a5b473 completed May 12, 2026, 11:17 p.m.
NED2 Entity disambiguation (via description) batch_6a03b5c09f4881909fb0ead5fc48895c completed May 12, 2026, 11:20 p.m.
Created at: April 10, 2026, 10:34 a.m.