Triple

T7424030
Position Surface form Disambiguated ID Type / Status
Subject If/Then E171322 entity
Predicate orchestrator P4735 FINISHED
Object Michael Starobin E310997 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: Michael Starobin | Statement: [If/Then, orchestrator, Michael Starobin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Starobin
Context triple: [If/Then, orchestrator, Michael Starobin]
  • A. Michael Starobin chosen
    Michael Starobin is a Tony Award–winning American orchestrator and arranger known for his work on numerous Broadway musicals.
  • B. Michael Rachmil
    Michael Rachmil is a film producer best known for his work on the 1987 romantic comedy "Roxanne" starring Steve Martin.
  • C. Michael Gelman
    Michael Gelman is a longtime American television producer best known for his work shaping and overseeing the daytime talk show "Live!" through its various host pairings.
  • D. Michael Kagan
    Michael Kagan is an Israeli technologist and entrepreneur best known as the co-founder and longtime chief technology officer of high-performance networking company Mellanox Technologies.
  • E. Mike Sokolsky
    Mike Sokolsky is a co-founder of the online education platform Udacity, known for its technology-focused courses and nanodegree programs.
  • 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_69c68a625d048190af70eb8b63bec5a0 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f2eece588190905774e7151edcb8 completed March 27, 2026, 9:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69c937a70a94819090ff91dfa463682b completed March 29, 2026, 2:31 p.m.
Created at: March 27, 2026, 3:12 p.m.