Triple

T10526293
Position Surface form Disambiguated ID Type / Status
Subject Superman IV: The Quest for Peace E248313 entity
Predicate producer P490 FINISHED
Object Yoram Globus E296900 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: Yoram Globus | Statement: [Superman IV: The Quest for Peace, producer, Yoram Globus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yoram Globus
Context triple: [Superman IV: The Quest for Peace, producer, Yoram Globus]
  • A. Yoram Globus chosen
    Yoram Globus is an Israeli film producer best known for his leadership of Cannon Films in the 1980s, during which he oversaw numerous action and genre movies.
  • B. Jeff Levine
    Jeff Levine is a film producer best known for his work on the horror drama "Shadow of the Vampire."
  • C. Gabe Kaplan
    Gabe Kaplan is an American comedian, actor, and professional poker player best known for starring as Gabe Kotter on the 1970s sitcom "Welcome Back, Kotter."
  • D. Larry Hillblom
    Larry Hillblom was an American businessman and entrepreneur best known as a co-founder of the global logistics and courier company DHL.
  • E. Nir Friedman
    Nir Friedman is a computer scientist and computational biologist known for his influential work on probabilistic graphical models and their applications to biological data.
  • 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_69d381c5c7448190bec34bee7ec72bac completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509f4bbe88190bce7789a56c85671 completed April 7, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69d90e26c4908190b77d73c11bee6119 completed April 10, 2026, 2:50 p.m.
Created at: April 6, 2026, 12:29 p.m.