Triple

T5467598
Position Surface form Disambiguated ID Type / Status
Subject de León E122750 entity
Predicate hasVariant P455 FINISHED
Object De León E122750 NE FINISHED

How this triple was built (2 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 León | Statement: [de León, hasVariant, De León]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: De León
Context triple: [de León, hasVariant, De León]
  • A. de León chosen
    De León is a Spanish surname of Sephardic Jewish origin historically associated with notable figures in religious and cultural scholarship.
  • B. De Leon
    De Leon is a surname of Spanish origin commonly borne by individuals and places in Spanish-speaking and former Spanish-colonial regions.
  • C. Al Olaya
    Al Olaya is a prominent commercial and business district in Riyadh, Saudi Arabia, known for its modern skyscrapers, upscale shopping, and major corporate offices.
  • D. Balderas
    Balderas is a major Mexico City Metro station known for its central location and high passenger traffic.
  • E. de Luna
    De Luna is the noble Aragonese family name of Pope Benedict XIII, reflecting his origins in the medieval Spanish aristocracy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bf70d919e08190a4fae4359cf8c951 completed March 22, 2026, 4:32 a.m.
Created at: March 20, 2026, 2:09 p.m.