Triple

T23511499
Position Surface form Disambiguated ID Type / Status
Subject Bruce Arians E572434 entity
Predicate employer P7 FINISHED
Object Arizona Cardinals 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: Arizona Cardinals | Statement: [Bruce Arians, employer, Arizona Cardinals]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arizona Cardinals
Context triple: [Bruce Arians, employer, Arizona Cardinals]
  • A. Arizona Cardinals chosen
    The Arizona Cardinals are a professional American football team based in the Phoenix metropolitan area that competes in the NFL’s NFC West division.
  • B. Arizona Colt
    Arizona Colt is a 1966 Italian Spaghetti Western film starring Giuliano Gemma as a skilled gunslinger navigating betrayal and revenge in the American frontier.
  • C. Broncos
    The Broncos are the athletic teams representing Rancho Bernardo High School in interscholastic sports competitions.
  • D. Broncos
    Broncos is the commonly used short name for the Brisbane Broncos, a professional rugby league club based in Brisbane, Australia.
  • E. Broncos
    The Broncos are the intercollegiate athletic teams that represent Santa Clara University in NCAA sports.
  • 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_69e245b5e4208190bac8a6509867e394 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1aa7e99b081909620c4f951100023 completed April 29, 2026, 6:51 a.m.
Created at: April 17, 2026, 6:07 p.m.