Triple

T4073587
Position Surface form Disambiguated ID Type / Status
Subject Manheim Auctions E86704 entity
Predicate hasCompetitor P1375 FINISHED
Object ADESA
ADESA is a major North American vehicle auction and remarketing company that provides wholesale used-vehicle auctions and related services to automotive dealers, manufacturers, and fleet operators.
 E411960 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: ADESA | Statement: [Manheim Auctions, hasCompetitor, ADESA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ADESA
Context triple: [Manheim Auctions, hasCompetitor, ADESA]
  • A. DASA
    DASA (Deutsche Aerospace AG) was a major German aerospace and defense company that became a core component of the later European aerospace giant Airbus Group.
  • B. AdE
    AdE is the abbreviation for the Akademio de Esperanto, the language-regulating body that oversees the evolution and norms of Esperanto.
  • C. EdA
    EdA is the commonly used abbreviation for the Spanish Air and Space Force, the aerial warfare branch of Spain's armed forces.
  • D. ASEA
    ASEA was a major Swedish electrical engineering and power company that became a global leader in industrial technology before merging to form ABB.
  • E. Ateso
    Ateso is a Nilotic language spoken primarily by the Teso people of eastern Uganda and western Kenya.
  • 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: ADESA
Triple: [Manheim Auctions, hasCompetitor, ADESA]
Generated description
ADESA is a major North American vehicle auction and remarketing company that provides wholesale used-vehicle auctions and related services to automotive dealers, manufacturers, and fleet operators.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ADESA
Target entity description: ADESA is a major North American vehicle auction and remarketing company that provides wholesale used-vehicle auctions and related services to automotive dealers, manufacturers, and fleet operators.
  • A. DASA
    DASA (Deutsche Aerospace AG) was a major German aerospace and defense company that became a core component of the later European aerospace giant Airbus Group.
  • B. AdE
    AdE is the abbreviation for the Akademio de Esperanto, the language-regulating body that oversees the evolution and norms of Esperanto.
  • C. EdA
    EdA is the commonly used abbreviation for the Spanish Air and Space Force, the aerial warfare branch of Spain's armed forces.
  • D. ASEA
    ASEA was a major Swedish electrical engineering and power company that became a global leader in industrial technology before merging to form ABB.
  • E. Ateso
    Ateso is a Nilotic language spoken primarily by the Teso people of eastern Uganda and western Kenya.
  • 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_69aed93ebe448190a1f1686e28740ac9 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefc245d888190ae773f9c3077953b completed March 9, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562bc05948190a9ad709768420588 completed March 14, 2026, 1:29 p.m.
NEDg Description generation batch_69b563b3db0481909f3dd2a9e6a88e6e completed March 14, 2026, 1:33 p.m.
NED2 Entity disambiguation (via description) batch_69b567e223cc8190aa1d7e827e6c70fd completed March 14, 2026, 1:51 p.m.
Created at: March 9, 2026, 3:39 p.m.