Triple

T22212943
Position Surface form Disambiguated ID Type / Status
Subject Al Cervi E549001 entity
Predicate familyName P18 FINISHED
Object Cervi NE NERFINISHED

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: Cervi | Statement: [Al Cervi, familyName, Cervi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cervi
Context triple: [Al Cervi, familyName, Cervi]
  • A. Cervi chosen
    Cervi is an Italian surname most notably associated with Al Cervi, a Hall of Fame American professional basketball player and coach.
  • B. Cervo
    Cervo is a river in the Piedmont region of northwestern Italy, known for flowing through the provinces of Biella and Vercelli before joining the Sesia.
  • C. Capra
    Capra is a genus of mammals that includes goats and wild goat-like species such as ibexes, known for their sure-footedness in mountainous terrain.
  • D. Capra walie
    Capra walie, commonly known as the Walia ibex, is an endangered wild goat species endemic to the highlands of Ethiopia.
  • E. Tule elk
    The tule elk is a subspecies of elk native to California, known for its recovery from near extinction and its preference for open grasslands and marshy habitats.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e3f7e04819089806d81d5ac431e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12b2d607c81909511761b5563ddee completed April 28, 2026, 9:48 p.m.
Created at: April 16, 2026, 8:37 p.m.