Triple

T1868911
Position Surface form Disambiguated ID Type / Status
Subject Catalonia E34986 entity
Predicate traditionalFestival P7822 FINISHED
Object Castells
Castells are a traditional Catalan cultural practice in which teams build and dismantle multi-tiered human towers at festivals and public celebrations.
 E208035 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: Castells | Statement: [Catalonia, traditionalFestival, Castells]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Castells
Context triple: [Catalonia, traditionalFestival, Castells]
  • A. Miquel
    Miquel is a given name, commonly used in Catalan and other languages, that corresponds to the English name Michael.
  • B. Antoni
    Antoni is a masculine given name of Latin origin, commonly used in Poland and other European countries.
  • C. Pérez-Castejón
    Pérez-Castejón is the compound surname of Spanish politician Pedro Sánchez, reflecting his paternal and maternal family lineages.
  • D. Val Badia
    Val Badia is a valley in the Dolomites of northern Italy known for its Ladin-speaking communities, alpine landscapes, and ski tourism.
  • E. Boyeros
    Boyeros is a municipality in Havana, Cuba, known for hosting the country’s main international gateway, José Martí International Airport.
  • 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: Castells
Triple: [Catalonia, traditionalFestival, Castells]
Generated description
Castells are a traditional Catalan cultural practice in which teams build and dismantle multi-tiered human towers at festivals and public celebrations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Castells
Target entity description: Castells are a traditional Catalan cultural practice in which teams build and dismantle multi-tiered human towers at festivals and public celebrations.
  • A. Miquel
    Miquel is a given name, commonly used in Catalan and other languages, that corresponds to the English name Michael.
  • B. Antoni
    Antoni is a masculine given name of Latin origin, commonly used in Poland and other European countries.
  • C. Pérez-Castejón
    Pérez-Castejón is the compound surname of Spanish politician Pedro Sánchez, reflecting his paternal and maternal family lineages.
  • D. Val Badia
    Val Badia is a valley in the Dolomites of northern Italy known for its Ladin-speaking communities, alpine landscapes, and ski tourism.
  • E. Boyeros
    Boyeros is a municipality in Havana, Cuba, known for hosting the country’s main international gateway, José Martí International Airport.
  • 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_69a88600b2f88190bc09303e68ab517e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb0b7e4548190a3761133fbbb7b81 completed March 7, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1dab2a481909adb0a3132348cee completed March 8, 2026, 7:45 p.m.
NEDg Description generation batch_69add25c9c208190a576cf1123c0a2e6 completed March 8, 2026, 7:47 p.m.
NED2 Entity disambiguation (via description) batch_69add32c32b08190be6624eefa2fa386 completed March 8, 2026, 7:51 p.m.
Created at: March 4, 2026, 7:34 p.m.