Triple

T20721499
Position Surface form Disambiguated ID Type / Status
Subject Beam Suntory E509323 entity
Predicate brand P1500 FINISHED
Object Sourz
Sourz is a popular range of brightly colored, fruit-flavored liqueurs known for their sweet-and-sour taste, commonly used as shots and in mixed drinks.
 E1446604 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: Sourz | Statement: [Beam Suntory, brand, Sourz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sourz
Context triple: [Beam Suntory, brand, Sourz]
  • A. Soure
    Soure is a Portuguese municipality located in the central region within the Coimbra District, known for its rural landscapes and historical heritage.
  • B. SOUR
    SOUR is Olivia Rodrigo’s debut studio album, a pop record blending confessional songwriting with themes of heartbreak, jealousy, and teenage angst.
  • C. Sour Suite
    "Sour Suite" is a reflective soft rock song by Canadian band The Guess Who, known for its melancholic tone and introspective lyrics.
  • D. La source
    La source is a 19th-century ballet composed by Léo Delibes (with contributions by Ludwig Minkus), known for its lyrical melodies and place in the Romantic ballet repertoire.
  • E. Cerca-la-Source
    Cerca-la-Source is a commune and town in Haiti located within the country's Centre Department.
  • 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: Sourz
Triple: [Beam Suntory, brand, Sourz]
Generated description
Sourz is a popular range of brightly colored, fruit-flavored liqueurs known for their sweet-and-sour taste, commonly used as shots and in mixed drinks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sourz
Target entity description: Sourz is a popular range of brightly colored, fruit-flavored liqueurs known for their sweet-and-sour taste, commonly used as shots and in mixed drinks.
  • A. Soure
    Soure is a Portuguese municipality located in the central region within the Coimbra District, known for its rural landscapes and historical heritage.
  • B. SOUR
    SOUR is Olivia Rodrigo’s debut studio album, a pop record blending confessional songwriting with themes of heartbreak, jealousy, and teenage angst.
  • C. Sour Suite
    "Sour Suite" is a reflective soft rock song by Canadian band The Guess Who, known for its melancholic tone and introspective lyrics.
  • D. La source
    La source is a 19th-century ballet composed by Léo Delibes (with contributions by Ludwig Minkus), known for its lyrical melodies and place in the Romantic ballet repertoire.
  • E. Cerca-la-Source
    Cerca-la-Source is a commune and town in Haiti located within the country's Centre Department.
  • 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_69e0b4c4cc648190b45fda6e2b20af56 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1d5eec08190832ffba8a90f3076 completed April 21, 2026, 12:16 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08e05734d88190b6386afc9e2e2d12 completed May 16, 2026, 9:23 p.m.
NEDg Description generation batch_6a08e101997881909ad7ed5e91cf1ed7 completed May 16, 2026, 9:26 p.m.
NED2 Entity disambiguation (via description) batch_6a08e1ba6cf08190a43b1d57ef061a72 completed May 16, 2026, 9:29 p.m.
Created at: April 16, 2026, 12:27 p.m.