Triple

T13823814
Position Surface form Disambiguated ID Type / Status
Subject Ricola Storage Building Laufen E332199 entity
Predicate client P27 FINISHED
Object Ricola
Ricola is a Swiss company best known for producing herbal cough drops and other herbal-based confectionery products.
 E1063693 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: Ricola | Statement: [Ricola Storage Building Laufen, client, Ricola]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ricola
Context triple: [Ricola Storage Building Laufen, client, Ricola]
  • A. Maleizen
    Maleizen is a village that forms a sub-municipality of Overijse in the Flemish Brabant province of Belgium.
  • B. Maggia
    The Maggia is a powerful fictional international crime syndicate in the Marvel Comics universe, often serving as a major organized-crime antagonist to superheroes like Iron Man and Spider-Man.
  • C. Maggia
    Maggia is a river in the Swiss canton of Ticino that flows from the Alps into Lake Maggiore.
  • D. Lipton
    Lipton is a globally recognized tea brand offering a wide range of tea products, including black, green, and herbal varieties.
  • E. Volvic
    Volvic is a French town in the Auvergne region best known worldwide for its natural mineral water sourced from volcanic springs.
  • 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: Ricola
Triple: [Ricola Storage Building Laufen, client, Ricola]
Generated description
Ricola is a Swiss company best known for producing herbal cough drops and other herbal-based confectionery products.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ricola
Target entity description: Ricola is a Swiss company best known for producing herbal cough drops and other herbal-based confectionery products.
  • A. Maleizen
    Maleizen is a village that forms a sub-municipality of Overijse in the Flemish Brabant province of Belgium.
  • B. Maggia
    The Maggia is a powerful fictional international crime syndicate in the Marvel Comics universe, often serving as a major organized-crime antagonist to superheroes like Iron Man and Spider-Man.
  • C. Maggia
    Maggia is a river in the Swiss canton of Ticino that flows from the Alps into Lake Maggiore.
  • D. Lipton
    Lipton is a globally recognized tea brand offering a wide range of tea products, including black, green, and herbal varieties.
  • E. Volvic
    Volvic is a French town in the Auvergne region best known worldwide for its natural mineral water sourced from volcanic springs.
  • 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_69d81c5ae7c88190b0dd41bdafeb5999 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0285fb7c8190be4b90bdc0d6fa53 completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b8e85c6c81908bdf5d43b917d151 completed May 3, 2026, 9:06 p.m.
NEDg Description generation batch_69f7b9d81f488190875e9b3f885556ab completed May 3, 2026, 9:10 p.m.
NED2 Entity disambiguation (via description) batch_69f7ba99ad9c8190906b6b63cf27a446 completed May 3, 2026, 9:14 p.m.
Created at: April 9, 2026, 10:13 p.m.