Triple

T19136605
Position Surface form Disambiguated ID Type / Status
Subject Yehoshua Kenaz E468450 entity
Predicate name P16 FINISHED
Object Yehoshua Kenaz 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: Yehoshua Kenaz | Statement: [Yehoshua Kenaz, name, Yehoshua Kenaz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yehoshua Kenaz
Context triple: [Yehoshua Kenaz, name, Yehoshua Kenaz]
  • A. Yehoshua Kenaz chosen
    Yehoshua Kenaz was a prominent Israeli novelist and translator known for his psychologically rich, realist depictions of Israeli society and military life.
  • B. Yehoshua Yevin
    Yehoshua Yevin was a Revisionist Zionist activist and leader associated with the militant underground in Mandatory Palestine.
  • C. Moshe Aviv
    Moshe Aviv was an Israeli businessman and real estate developer best known for his major role in shaping modern Israeli urban skylines.
  • D. Gil Tene
    Gil Tene is a software engineer and entrepreneur best known as the co-founder and CTO of Azul Systems and for his work on Java performance and low-latency garbage collection.
  • E. Ben Yehoyada
    Ben Yehoyada is a classic kabbalistic and ethical commentary on the Talmudic aggadot, authored by the renowned Baghdadi sage Ben Ish Chai (Rabbi Yosef Chaim of Baghdad).
  • 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_69d8dd0796a48190b34ce4cd9d3f3be5 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e3edd1c48190b86bef530ebbd092 completed April 20, 2026, 8:29 a.m.
Created at: April 10, 2026, 12:05 p.m.