Triple

T23126714
Position Surface form Disambiguated ID Type / Status
Subject Thomas Michael Izzo E577049 entity
Predicate notableStudent P4838 FINISHED
Object Mateen Cleaves 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: Mateen Cleaves | Statement: [Thomas Michael Izzo, notableStudent, Mateen Cleaves]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mateen Cleaves
Context triple: [Thomas Michael Izzo, notableStudent, Mateen Cleaves]
  • A. Mateen Cleaves chosen
    Mateen Cleaves is a former Michigan State University basketball star and NBA guard best known for leading the Spartans to the 2000 national championship.
  • B. Kareem Campbell
    Kareem Campbell is an American professional skateboarder known for his influential street skating style and signature tricks, including the "Ghetto Bird."
  • C. Hakeem Campbell
    Hakeem Campbell is a main supporting character on the sitcom "Moesha," known as Moesha's loyal, humorous best friend and neighbor.
  • D. Jamal Hill
    Jamal Hill is an American film director known for his work in urban drama and independent cinema.
  • E. Cedric Yarbrough
    Cedric Yarbrough is an American actor and comedian best known for his roles on the TV series "Reno 911!" and for voicing characters in animated shows such as "The Boondocks."
  • 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_69e245f7b0e481909c473ff4e6a54e2c completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18e5482588190b95b36075ecc7f24 completed April 29, 2026, 4:51 a.m.
Created at: April 17, 2026, 3:59 p.m.