Triple

T6352821
Position Surface form Disambiguated ID Type / Status
Subject Liège E142916 entity
Predicate notableDrink P4038 FINISHED
Object Peket
Peket is a traditional juniper-flavored spirit from the Liège region of Belgium, often enjoyed as a local specialty at festivals and bars.
E586084 NE FINISHED

How this triple was built (5 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: Peket | Statement: [Liège, notableDrink, Peket]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peket
Context triple: [Liège, notableDrink, Peket]
  • A. Pekat
    Pekat is a settlement on the Indonesian island of Sumbawa that was devastated by the catastrophic 1815 eruption of Mount Tambora.
  • B. Pekar
    Pekar is a surname of Central or Eastern European origin, notably associated with several cultural and artistic figures.
  • C. Penge
    Penge is a suburban district in southeast London known for its Victorian architecture and proximity to Crystal Palace.
  • D. Pesa
    Pesa is a Polish manufacturer of rail vehicles, particularly known for producing modern trams and trains used in various European cities.
  • E. PEK
    PEK is the IATA airport code for Beijing Capital International Airport, one of the busiest and largest aviation hubs in China and 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: Peket
Triple: [Liège, notableDrink, Peket]
Generated description
Peket is a traditional juniper-flavored spirit from the Liège region of Belgium, often enjoyed as a local specialty at festivals and bars.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Peket
Target entity description: Peket is a traditional juniper-flavored spirit from the Liège region of Belgium, often enjoyed as a local specialty at festivals and bars.
  • A. Pekat
    Pekat is a settlement on the Indonesian island of Sumbawa that was devastated by the catastrophic 1815 eruption of Mount Tambora.
  • B. Pekar
    Pekar is a surname of Central or Eastern European origin, notably associated with several cultural and artistic figures.
  • C. Penge
    Penge is a suburban district in southeast London known for its Victorian architecture and proximity to Crystal Palace.
  • D. Pesa
    Pesa is a Polish manufacturer of rail vehicles, particularly known for producing modern trams and trains used in various European cities.
  • E. PEK
    PEK is the IATA airport code for Beijing Capital International Airport, one of the busiest and largest aviation hubs in China and the world.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: notableDrink
Context triple: [Liège, notableDrink, Peket]
  • A. traditionalDrink chosen
    Indicates that one entity is a beverage customarily consumed within the culture, heritage, or longstanding practices associated with another entity.
  • B. drinks
    Indicates that one entity consumes a liquid substance, typically by ingesting it through the mouth.
  • C. notableDrinker
    Indicates that the subject is known or recognized for their drinking behavior, typically due to frequency, quantity, or notoriety.
  • D. hasDrinkNamedAfter
    Indicates that one entity has a beverage that is named after another entity.
  • E. madeWithAlcohol
    Indicates that something is created, prepared, or produced using alcohol as an ingredient or component.
  • F. None of above.

Provenance (6 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_69c008d6dcbc8190aa1c2f1fd8916b42 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c067dec4a88190992d57a0cc7782ad completed March 22, 2026, 10:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69c60459a7c081909b551dcf1735bf75 completed March 27, 2026, 4:15 a.m.
NEDg Description generation batch_69c605212688819081fc8f9c1500ff50 completed March 27, 2026, 4:18 a.m.
NED2 Entity disambiguation (via description) batch_69c605c0db308190960370a81ff8123b completed March 27, 2026, 4:21 a.m.
PD Predicate disambiguation batch_69c060ec091c8190912aac44e1b8b1c9 completed March 22, 2026, 9:36 p.m.
Created at: March 22, 2026, 4:31 p.m.