Triple

T5933485
Position Surface form Disambiguated ID Type / Status
Subject Danone E131990 entity
Predicate hasBrand P1500 FINISHED
Object Actimel
Actimel is a probiotic yogurt drink brand known for its small bottled dairy shots marketed to support the immune system.
 E559705 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: Actimel | Statement: [Danone, hasBrand, Actimel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Actimel
Context triple: [Danone, hasBrand, Actimel]
  • A. Activia
    Activia is a popular probiotic yogurt brand known for supporting digestive health, produced and marketed by Danone.
  • B. Alpro
    Alpro is a European food company best known for its plant-based drinks, yogurts, and other dairy alternatives made primarily from soy, oats, and almonds.
  • C. Milk
    Milk is a 2008 biographical film about gay rights activist and politician Harvey Milk, directed by Gus Van Sant and starring Sean Penn.
  • D. Aptamil
    Aptamil is a popular infant and toddler formula brand known for its nutritionally tailored milk products for early childhood.
  • E. Yakult Atoms
    Yakult Atoms was the former name of the professional Japanese baseball team now known as the Tokyo Yakult Swallows.
  • 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: Actimel
Triple: [Danone, hasBrand, Actimel]
Generated description
Actimel is a probiotic yogurt drink brand known for its small bottled dairy shots marketed to support the immune system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Actimel
Target entity description: Actimel is a probiotic yogurt drink brand known for its small bottled dairy shots marketed to support the immune system.
  • A. Activia
    Activia is a popular probiotic yogurt brand known for supporting digestive health, produced and marketed by Danone.
  • B. Alpro
    Alpro is a European food company best known for its plant-based drinks, yogurts, and other dairy alternatives made primarily from soy, oats, and almonds.
  • C. Milk
    Milk is a 2008 biographical film about gay rights activist and politician Harvey Milk, directed by Gus Van Sant and starring Sean Penn.
  • D. Aptamil
    Aptamil is a popular infant and toddler formula brand known for its nutritionally tailored milk products for early childhood.
  • E. Yakult Atoms
    Yakult Atoms was the former name of the professional Japanese baseball team now known as the Tokyo Yakult Swallows.
  • 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_69c0085c55dc8190aa90e242c956e2fa completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0389f6fc881909527b928838ffcdd completed March 22, 2026, 6:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e3affd748190a37e3cc60e58d6a6 completed March 23, 2026, 6:54 a.m.
NEDg Description generation batch_69c0f85e33d8819080d9d721421b4c5b completed March 23, 2026, 8:22 a.m.
NED2 Entity disambiguation (via description) batch_69c0fad0bdf08190bf6599d492848582 completed March 23, 2026, 8:33 a.m.
Created at: March 22, 2026, 4 p.m.