Triple

T20245745
Position Surface form Disambiguated ID Type / Status
Subject Mlynská dolina campus E498419 entity
Predicate hasPart P35 FINISHED
Object canteen "Menza"
Canteen "Menza" is a student dining facility located on the Mlynská dolina university campus, serving affordable meals to students and staff.
 E1418874 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: canteen "Menza" | Statement: [Mlynská dolina campus, hasPart, canteen "Menza"]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: canteen "Menza"
Context triple: [Mlynská dolina campus, hasPart, canteen "Menza"]
  • A. Maras Restaurant
    Maras Restaurant is an upscale dining venue in Lima, Peru, known for contemporary Peruvian cuisine and located within The Westin Lima Hotel.
  • B. Tito’s
    "Tito’s" is a song by Canadian singer-songwriter Jessie Reyez, known for her raw, emotional lyricism and distinctive vocal style.
  • C. Saló de Cent
    Saló de Cent is a historic Gothic ceremonial hall in Barcelona’s city hall, renowned as a former meeting place of the medieval city council.
  • D. Fontanafredda
    Fontanafredda is a historic estate and wine-producing property in the Piedmont region of Italy, closely associated with the royal House of Savoy.
  • E. Menuhin
    Menuhin is a surname most famously associated with Yehudi Menuhin, the renowned 20th-century violinist and conductor.
  • 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: canteen "Menza"
Triple: [Mlynská dolina campus, hasPart, canteen "Menza"]
Generated description
Canteen "Menza" is a student dining facility located on the Mlynská dolina university campus, serving affordable meals to students and staff.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: canteen "Menza"
Target entity description: Canteen "Menza" is a student dining facility located on the Mlynská dolina university campus, serving affordable meals to students and staff.
  • A. Maras Restaurant
    Maras Restaurant is an upscale dining venue in Lima, Peru, known for contemporary Peruvian cuisine and located within The Westin Lima Hotel.
  • B. Tito’s
    "Tito’s" is a song by Canadian singer-songwriter Jessie Reyez, known for her raw, emotional lyricism and distinctive vocal style.
  • C. Saló de Cent
    Saló de Cent is a historic Gothic ceremonial hall in Barcelona’s city hall, renowned as a former meeting place of the medieval city council.
  • D. Fontanafredda
    Fontanafredda is a historic estate and wine-producing property in the Piedmont region of Italy, closely associated with the royal House of Savoy.
  • E. Menuhin
    Menuhin is a surname most famously associated with Yehudi Menuhin, the renowned 20th-century violinist and conductor.
  • 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_69da6274c58c81909c646eabed6f4f30 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e673a26c8481908f408fb6426aece9 completed April 20, 2026, 6:42 p.m.
NED1 Entity disambiguation (via context triple) batch_6a084b98184c8190bdcb5f121dfa43fa completed May 16, 2026, 10:48 a.m.
NEDg Description generation batch_6a084c26941c8190bd0588b14e2b6b86 completed May 16, 2026, 10:51 a.m.
NED2 Entity disambiguation (via description) batch_6a084cab68848190af316bb7837b1532 completed May 16, 2026, 10:53 a.m.
Created at: April 11, 2026, 11:40 p.m.