Triple

T15702308
Position Surface form Disambiguated ID Type / Status
Subject Up in Smoke E380621 entity
Predicate mainCharacter P1183 FINISHED
Object Pedro De Pacas E1114900 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: Pedro De Pacas | Statement: [Up in Smoke, mainCharacter, Pedro De Pacas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pedro De Pacas
Context triple: [Up in Smoke, mainCharacter, Pedro De Pacas]
  • A. Pedro De Pacas chosen
    Pedro De Pacas is a laid-back, perpetually stoned Chicano character portrayed by Cheech Marin in the classic stoner comedy film "Up in Smoke."
  • B. Diego de Villarroel
    Diego de Villarroel was a Spanish colonial officer best known for founding the city of San Miguel de Tucumán in present-day Argentina in the 16th century.
  • C. Juan de Pimentel
    Juan de Pimentel was a Spanish colonial official who served as a leading military and administrative authority in Venezuela during the period of Spanish rule.
  • D. Martín de Osambela
    Martín de Osambela was a prominent Spanish merchant and landowner in colonial Lima, Peru, known for his wealth and influence in the late 18th and early 19th centuries.
  • E. de Saavedra
    de Saavedra is a Spanish surname historically associated with notable figures in Spain and its overseas territories.
  • 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_69d86d99e860819094b6957cde470f2c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f6e965881909319f85c51c6fb74 completed April 16, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff7577a3348190912fad48f7d8599e completed May 9, 2026, 5:57 p.m.
Created at: April 10, 2026, 4:45 a.m.