Triple

T12857236
Position Surface form Disambiguated ID Type / Status
Subject Migros E307487 entity
Predicate hasBrand P1500 FINISHED
Object Sélection
Sélection is Migros’ premium private-label brand offering high-quality, often gourmet food and specialty products.
 E1006147 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: Sélection | Statement: [Migros, hasBrand, Sélection]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sélection
Context triple: [Migros, hasBrand, Sélection]
  • A. Choix
    Choix is a municipality and town located in the northern part of the Mexican state of Sinaloa, known for its mountainous terrain and proximity to the Sierra Madre Occidental.
  • B. Le Select
    Le Select is a historic Parisian café in the Montparnasse district, long associated with artists, writers, and intellectuals.
  • C. MatSelect
    MatSelect is an Angular Material UI component that provides a styled, accessible dropdown selection control for Angular applications.
  • D. SCELSE
    SCELSE is a Singapore-based interdisciplinary research centre focused on environmental life sciences and engineering, particularly the study and application of microbial communities in natural and engineered ecosystems.
  • E. SeleQtions
    SeleQtions is a distinctive collection of upscale and heritage hotels and resorts operated under the Taj Hotels umbrella.
  • 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: Sélection
Triple: [Migros, hasBrand, Sélection]
Generated description
Sélection is Migros’ premium private-label brand offering high-quality, often gourmet food and specialty products.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sélection
Target entity description: Sélection is Migros’ premium private-label brand offering high-quality, often gourmet food and specialty products.
  • A. Choix
    Choix is a municipality and town located in the northern part of the Mexican state of Sinaloa, known for its mountainous terrain and proximity to the Sierra Madre Occidental.
  • B. Le Select
    Le Select is a historic Parisian café in the Montparnasse district, long associated with artists, writers, and intellectuals.
  • C. MatSelect
    MatSelect is an Angular Material UI component that provides a styled, accessible dropdown selection control for Angular applications.
  • D. SCELSE
    SCELSE is a Singapore-based interdisciplinary research centre focused on environmental life sciences and engineering, particularly the study and application of microbial communities in natural and engineered ecosystems.
  • E. SeleQtions
    SeleQtions is a distinctive collection of upscale and heritage hotels and resorts operated under the Taj Hotels umbrella.
  • 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_69d7bdf5e7cc8190be357278bc5ba3bb completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d970231ce48190a4eabc4b8c24a3ff completed April 10, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f69ba9a53c81908e9ed120f6cb94af completed May 3, 2026, 12:49 a.m.
NEDg Description generation batch_69f69d4a2ab481908460797a8ee6bc8d completed May 3, 2026, 12:56 a.m.
NED2 Entity disambiguation (via description) batch_69f69dc8b86c81908557fa8538e942de completed May 3, 2026, 12:58 a.m.
Created at: April 9, 2026, 5:37 p.m.