Triple

T12810334
Position Surface form Disambiguated ID Type / Status
Subject Groupama Stadium E306253 entity
Predicate sponsor P67 FINISHED
Object Groupama
Groupama is a major French mutual insurance and financial services group known for its extensive network and sponsorship activities in sports and culture.
 E1005011 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: Groupama | Statement: [Groupama Stadium, sponsor, Groupama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Groupama
Context triple: [Groupama Stadium, sponsor, Groupama]
  • A. BNP Paribas Cardif
    BNP Paribas Cardif is the insurance subsidiary of the BNP Paribas banking group, specializing in savings and protection insurance solutions worldwide.
  • B. AXA
    AXA is a major French multinational insurance and asset management company headquartered in Paris.
  • C. Allianz
    Allianz is a leading global financial services company, best known as one of the world’s largest insurance and asset management providers.
  • D. Swiss Re
    Swiss Re is a leading global reinsurance company headquartered in Zurich, Switzerland, providing risk transfer and insurance solutions worldwide.
  • E. Harmonie Mutuelle Semi de Paris
    Harmonie Mutuelle Semi de Paris is a major annual half marathon held in Paris, France, attracting tens of thousands of runners from around the world.
  • 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: Groupama
Triple: [Groupama Stadium, sponsor, Groupama]
Generated description
Groupama is a major French mutual insurance and financial services group known for its extensive network and sponsorship activities in sports and culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Groupama
Target entity description: Groupama is a major French mutual insurance and financial services group known for its extensive network and sponsorship activities in sports and culture.
  • A. BNP Paribas Cardif
    BNP Paribas Cardif is the insurance subsidiary of the BNP Paribas banking group, specializing in savings and protection insurance solutions worldwide.
  • B. AXA
    AXA is a major French multinational insurance and asset management company headquartered in Paris.
  • C. Allianz
    Allianz is a leading global financial services company, best known as one of the world’s largest insurance and asset management providers.
  • D. Swiss Re
    Swiss Re is a leading global reinsurance company headquartered in Zurich, Switzerland, providing risk transfer and insurance solutions worldwide.
  • E. Harmonie Mutuelle Semi de Paris
    Harmonie Mutuelle Semi de Paris is a major annual half marathon held in Paris, France, attracting tens of thousands of runners from around the world.
  • 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_69d7bdf46c448190b1faa55aaacb6317 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e817598819080fdd61e9d61236e completed April 10, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68ec89eb081909915af6e2216e0a2 completed May 2, 2026, 11:54 p.m.
NEDg Description generation batch_69f68fb6790881908c1d6f53b54906a2 completed May 2, 2026, 11:58 p.m.
NED2 Entity disambiguation (via description) batch_69f690c0bd208190bd1f04a9640ad1ce completed May 3, 2026, 12:03 a.m.
Created at: April 9, 2026, 5:31 p.m.