Triple

T17150222
Position Surface form Disambiguated ID Type / Status
Subject La Seu d’Urgell E416199 entity
Predicate near P350 FINISHED
Object Sort
Sort is a small town in the Catalan Pyrenees of northeastern Spain, known as a gateway to mountain landscapes and outdoor activities.
E1252090 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: Sort | Statement: [La Seu d’Urgell, near, Sort]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sort
Context triple: [La Seu d’Urgell, near, Sort]
  • A. MatSort
    MatSort is an Angular Material directive that adds sorting capabilities to data tables and other collections by managing and emitting sort state changes.
  • B. Sortu
    Sortu is a left-wing Basque nationalist political party that advocates for Basque self-determination and social justice.
  • C. Tarea Ordenamiento
    Tarea Ordenamiento was a major Cuban economic reform program that eliminated the dual-currency system, devalued the peso, and overhauled wages, prices, and subsidies starting in 2021.
  • D. Sortlending
    Sortlending is the Norwegian demonym for inhabitants of the town and municipality of Sortland in Nordland county, Norway.
  • E. Merge sort
    Merge sort is a comparison-based, divide-and-conquer sorting algorithm that recursively splits a list into halves, sorts them, and then merges the sorted halves into a fully ordered sequence.
  • 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: Sort
Triple: [La Seu d’Urgell, near, Sort]
Generated description
Sort is a small town in the Catalan Pyrenees of northeastern Spain, known as a gateway to mountain landscapes and outdoor activities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sort
Target entity description: Sort is a small town in the Catalan Pyrenees of northeastern Spain, known as a gateway to mountain landscapes and outdoor activities.
  • A. MatSort
    MatSort is an Angular Material directive that adds sorting capabilities to data tables and other collections by managing and emitting sort state changes.
  • B. Sortu
    Sortu is a left-wing Basque nationalist political party that advocates for Basque self-determination and social justice.
  • C. Tarea Ordenamiento
    Tarea Ordenamiento was a major Cuban economic reform program that eliminated the dual-currency system, devalued the peso, and overhauled wages, prices, and subsidies starting in 2021.
  • D. Sortlending
    Sortlending is the Norwegian demonym for inhabitants of the town and municipality of Sortland in Nordland county, Norway.
  • E. Merge sort
    Merge sort is a comparison-based, divide-and-conquer sorting algorithm that recursively splits a list into halves, sorts them, and then merges the sorted halves into a fully ordered sequence.
  • 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_69d886d279c081909f8ff1f743ddeb69 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f4067470819084aa233c4c4a6d4f completed April 18, 2026, 9:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01415b1d7c81908d000b0362042687 completed May 11, 2026, 2:39 a.m.
NEDg Description generation batch_6a0141b73e008190be8aa85dec1ba517 completed May 11, 2026, 2:40 a.m.
NED2 Entity disambiguation (via description) batch_6a01421d159c819096efc46fa08a48b9 completed May 11, 2026, 2:42 a.m.
Created at: April 10, 2026, 5:36 a.m.