Triple

T13989811
Position Surface form Disambiguated ID Type / Status
Subject Orval Abbey E336539 entity
Predicate knownFor P22 FINISHED
Object Orval beer
Orval beer is a renowned Trappist ale from Belgium, celebrated for its distinctive dry, hoppy, and Brett-influenced character.
 E1073531 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: Orval beer | Statement: [Orval Abbey, knownFor, Orval beer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Orval beer
Context triple: [Orval Abbey, knownFor, Orval beer]
  • A. Zorok Beer
    Zorok Beer is a lager brand produced by Asia Pacific Breweries, known for its easy-drinking taste and presence in several Asian markets.
  • B. Budweis
    Budweis is the German name for České Budějovice, a historic city in the Czech Republic renowned for its brewing tradition and medieval architecture.
  • C. Carlby
    Carlby is a small rural village and civil parish in the South Kesteven district of Lincolnshire, England.
  • D. Snow Beer
    Snow Beer is a popular Chinese lager that has become one of the world’s best-selling beer brands by volume.
  • E. Bintang Beer
    Bintang Beer is a popular Indonesian pale lager, often associated with the country’s major beer brand and widely consumed by locals and tourists alike.
  • 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: Orval beer
Triple: [Orval Abbey, knownFor, Orval beer]
Generated description
Orval beer is a renowned Trappist ale from Belgium, celebrated for its distinctive dry, hoppy, and Brett-influenced character.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Orval beer
Target entity description: Orval beer is a renowned Trappist ale from Belgium, celebrated for its distinctive dry, hoppy, and Brett-influenced character.
  • A. Zorok Beer
    Zorok Beer is a lager brand produced by Asia Pacific Breweries, known for its easy-drinking taste and presence in several Asian markets.
  • B. Budweis
    Budweis is the German name for České Budějovice, a historic city in the Czech Republic renowned for its brewing tradition and medieval architecture.
  • C. Carlby
    Carlby is a small rural village and civil parish in the South Kesteven district of Lincolnshire, England.
  • D. Snow Beer
    Snow Beer is a popular Chinese lager that has become one of the world’s best-selling beer brands by volume.
  • E. Bintang Beer
    Bintang Beer is a popular Indonesian pale lager, often associated with the country’s major beer brand and widely consumed by locals and tourists alike.
  • 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_69d81c639e808190a0e4b4f3d31c6a59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2eb22e388190904fc87765176c91 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac9604cc819088cde0ad8271ad48 completed May 6, 2026, 9:03 p.m.
NEDg Description generation batch_69fbad35be6c8190aa329fa947cbdcd9 completed May 6, 2026, 9:05 p.m.
NED2 Entity disambiguation (via description) batch_69fbae42ef2c8190b653d95de94042bc completed May 6, 2026, 9:10 p.m.
Created at: April 9, 2026, 10:18 p.m.