Triple

T6240465
Position Surface form Disambiguated ID Type / Status
Subject Mauthausen concentration camp E139585 entity
Predicate hasSubcamp P747 FINISHED
Object Gusen III
Gusen III was a subcamp of the Nazi Mauthausen concentration camp complex, used for forced labor under brutal conditions during World War II.
E582353 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: Gusen III | Statement: [Mauthausen concentration camp, hasSubcamp, Gusen III]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gusen III
Context triple: [Mauthausen concentration camp, hasSubcamp, Gusen III]
  • A. Gusen I
    Gusen I was a major Nazi concentration camp in Austria, notorious for its brutal forced labor, extremely high death rate, and role in the Mauthausen camp complex during World War II.
  • B. Gusen II
    Gusen II was a brutal Nazi concentration camp subcamp in Austria where prisoners endured extreme forced labor, starvation, and mass murder during World War II.
  • C. Gunta
    Gunta is a given name most notably borne by Gunta Stölzl, a pioneering textile artist and the only female master at the Bauhaus school.
  • D. Gavar
    Gavar is a town in Armenia that serves as a regional center near Lake Sevan in the Gegharkunik Province.
  • E. Ganguise
    Ganguise is a watercourse in southern France that feeds the artificial reservoir known as Lac de la Ganguise.
  • 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: Gusen III
Triple: [Mauthausen concentration camp, hasSubcamp, Gusen III]
Generated description
Gusen III was a subcamp of the Nazi Mauthausen concentration camp complex, used for forced labor under brutal conditions during World War II.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gusen III
Target entity description: Gusen III was a subcamp of the Nazi Mauthausen concentration camp complex, used for forced labor under brutal conditions during World War II.
  • A. Gusen I
    Gusen I was a major Nazi concentration camp in Austria, notorious for its brutal forced labor, extremely high death rate, and role in the Mauthausen camp complex during World War II.
  • B. Gusen II
    Gusen II was a brutal Nazi concentration camp subcamp in Austria where prisoners endured extreme forced labor, starvation, and mass murder during World War II.
  • C. Gunta
    Gunta is a given name most notably borne by Gunta Stölzl, a pioneering textile artist and the only female master at the Bauhaus school.
  • D. Gavar
    Gavar is a town in Armenia that serves as a regional center near Lake Sevan in the Gegharkunik Province.
  • E. Ganguise
    Ganguise is a watercourse in southern France that feeds the artificial reservoir known as Lac de la Ganguise.
  • 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_69c008b1c5088190ae6de2555fc05ad8 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c063067d9c819085a18d9d03939266 completed March 22, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5190e0a6481909e5372334a851770 completed March 26, 2026, 11:31 a.m.
NEDg Description generation batch_69c51b947088819089242ce511e2c639 completed March 26, 2026, 11:42 a.m.
NED2 Entity disambiguation (via description) batch_69c5843fd33c8190be48371960cfbfbb completed March 26, 2026, 7:08 p.m.
Created at: March 22, 2026, 4:23 p.m.