Triple

T7773626
Position Surface form Disambiguated ID Type / Status
Subject Jim Leyland E179133 entity
Predicate child P120 FINISHED
Object Kellie Leyland E179133 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: Kellie Leyland | Statement: [Jim Leyland, child, Kellie Leyland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kellie Leyland
Context triple: [Jim Leyland, child, Kellie Leyland]
  • A. Kellie Leyland chosen
    Kellie Leyland is known as the daughter of longtime Major League Baseball manager Jim Leyland.
  • B. Katie Leyland
    Katie Leyland is known as the wife of longtime Major League Baseball manager Jim Leyland.
  • C. Kimberlea Cloughley
    Kimberlea Cloughley is an American photographer best known for her marriage to actor Tommy Lee Jones.
  • D. Kellie Miller
    Kellie Miller is one of the plaintiffs who challenged Tennessee’s ban on recognizing same-sex marriages in the federal court case Tanco v. Haslam.
  • E. Lindsay Drummond
    Lindsay Drummond was a British publishing house known for issuing significant historical and political works, including Jawaharlal Nehru’s "Glimpses of World History."
  • 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_69c69f30602c819082ab52cd4af5c592 completed March 27, 2026, 3:16 p.m.
NER Named-entity recognition batch_69c70461b3e48190bf1e4d4f9e6bb08e completed March 27, 2026, 10:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8d6d65e308190924c05df5a0a4959 completed March 29, 2026, 7:37 a.m.
Created at: March 27, 2026, 4:11 p.m.