Triple

T8489321
Position Surface form Disambiguated ID Type / Status
Subject Iveco E200926 entity
Predicate formedByMergerOf P77 FINISHED
Object Unic
Unic was a French manufacturer of commercial vehicles, particularly trucks and buses, that later became part of the Iveco group through a merger.
 E737297 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: Unic | Statement: [Iveco, formedByMergerOf, Unic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Unic
Context triple: [Iveco, formedByMergerOf, Unic]
  • A. UNIKA
    UNIKA is the commonly used abbreviation for Soegijapranata Catholic University, a private Catholic higher education institution in Indonesia.
  • B. Unish
    Unish is a small settlement located on the Waternish peninsula of the Isle of Skye in Scotland.
  • C. Singur
    Singur is a town in West Bengal, India, known nationally for its role in a major land acquisition and industrialization controversy involving the proposed Tata Nano car factory.
  • D. Lunice
    Lunice is a Canadian electronic music producer and DJ known for his innovative trap-influenced beats and as one half of the duo TNGHT.
  • E. UNWE
    UNWE is a leading Bulgarian higher education institution in Sofia specializing in economics, business, and social sciences.
  • 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: Unic
Triple: [Iveco, formedByMergerOf, Unic]
Generated description
Unic was a French manufacturer of commercial vehicles, particularly trucks and buses, that later became part of the Iveco group through a merger.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Unic
Target entity description: Unic was a French manufacturer of commercial vehicles, particularly trucks and buses, that later became part of the Iveco group through a merger.
  • A. UNIKA
    UNIKA is the commonly used abbreviation for Soegijapranata Catholic University, a private Catholic higher education institution in Indonesia.
  • B. Unish
    Unish is a small settlement located on the Waternish peninsula of the Isle of Skye in Scotland.
  • C. Singur
    Singur is a town in West Bengal, India, known nationally for its role in a major land acquisition and industrialization controversy involving the proposed Tata Nano car factory.
  • D. Lunice
    Lunice is a Canadian electronic music producer and DJ known for his innovative trap-influenced beats and as one half of the duo TNGHT.
  • E. UNWE
    UNWE is a leading Bulgarian higher education institution in Sofia specializing in economics, business, and social sciences.
  • 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_69ca831d7b148190a6e32c1de43ab13b completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe5581d308190b47d76dd49a36529 completed March 31, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce3a4e5be48190b5c598123ef75f8b completed April 2, 2026, 9:43 a.m.
NEDg Description generation batch_69ce3d0323248190a076a209df98c96c completed April 2, 2026, 9:55 a.m.
NED2 Entity disambiguation (via description) batch_69ce3d7909f48190a46f58fca75d7740 completed April 2, 2026, 9:57 a.m.
Created at: March 30, 2026, 6:13 p.m.