Triple

T5467597
Position Surface form Disambiguated ID Type / Status
Subject de León E122750 entity
Predicate hasVariant P455 FINISHED
Object De Leon
De Leon is a surname of Spanish origin commonly borne by individuals and places in Spanish-speaking and former Spanish-colonial regions.
 E523837 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: De Leon | Statement: [de León, hasVariant, De Leon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: De Leon
Context triple: [de León, hasVariant, De Leon]
  • A. Balderas
    Balderas is a major Mexico City Metro station known for its central location and high passenger traffic.
  • B. Calvillo
    Calvillo is a municipality in the Mexican state of Aguascalientes, known for its guava production, colonial architecture, and surrounding natural landscapes.
  • C. Garza
    Garza is a Spanish-language surname of Basque origin that is common in Mexico and among people of Hispanic heritage.
  • D. Cristóbal Mendoza
    Cristóbal Mendoza was a Venezuelan lawyer and statesman who became the first head of state of independent Venezuela during the early 19th-century independence movement.
  • E. Gallegos
    Gallegos is a Spanish-language surname most notably associated with Venezuelan novelist and former president Rómulo Gallegos.
  • 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: De Leon
Triple: [de León, hasVariant, De Leon]
Generated description
De Leon is a surname of Spanish origin commonly borne by individuals and places in Spanish-speaking and former Spanish-colonial regions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: De Leon
Target entity description: De Leon is a surname of Spanish origin commonly borne by individuals and places in Spanish-speaking and former Spanish-colonial regions.
  • A. Balderas
    Balderas is a major Mexico City Metro station known for its central location and high passenger traffic.
  • B. Calvillo
    Calvillo is a municipality in the Mexican state of Aguascalientes, known for its guava production, colonial architecture, and surrounding natural landscapes.
  • C. Garza
    Garza is a Spanish-language surname of Basque origin that is common in Mexico and among people of Hispanic heritage.
  • D. Cristóbal Mendoza
    Cristóbal Mendoza was a Venezuelan lawyer and statesman who became the first head of state of independent Venezuela during the early 19th-century independence movement.
  • E. Gallegos
    Gallegos is a Spanish-language surname most notably associated with Venezuelan novelist and former president Rómulo Gallegos.
  • 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_69bd4643f16081908d7f29e08096115a completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd9218621c819093267a012bd49a35 completed March 20, 2026, 6:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf6c737eb88190bcec6f257f653d32 completed March 22, 2026, 4:13 a.m.
NEDg Description generation batch_69bf6dab32fc81909034d78a8813c238 completed March 22, 2026, 4:18 a.m.
NED2 Entity disambiguation (via description) batch_69bf6e15a9888190a2423bd5573d9d29 completed March 22, 2026, 4:20 a.m.
Created at: March 20, 2026, 2:09 p.m.