Triple

T9896859
Position Surface form Disambiguated ID Type / Status
Subject Ziv Aviram E182196 entity
Predicate coFounderWith P2835 FINISHED
Object Amnon Shashua E172886 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: Amnon Shashua | Statement: [Ziv Aviram, coFounderWith, Amnon Shashua]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amnon Shashua
Context triple: [Ziv Aviram, coFounderWith, Amnon Shashua]
  • A. Amnon Shashua chosen
    Amnon Shashua is an Israeli computer scientist and entrepreneur best known as the co-founder and CEO of Mobileye, a leading company in advanced driver-assistance and autonomous driving technologies.
  • B. Oded Maler
    Oded Maler is a computer scientist known for his contributions to formal verification, hybrid systems, and real-time systems theory.
  • C. Yehuda Efroni
    Yehuda Efroni was an Israeli actor known for his work in film, television, and theater.
  • D. Menahem Golan
    Menahem Golan was an Israeli film producer and director best known for co-founding Cannon Films and producing numerous action and genre movies in the 1980s.
  • E. Arnon Grunberg
    Arnon Grunberg is a Dutch novelist, essayist, and columnist known for his darkly comic, psychologically incisive works that explore themes of identity, war, and human vulnerability.
  • 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_69ca82876f8081909cf75df0f99bb13f completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cdb4ab15f881909f75a8e01051dbc4 completed April 2, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d20d92624c81909f5a8af8703ead09 completed April 5, 2026, 7:21 a.m.
Created at: March 30, 2026, 8:40 p.m.