Triple

T9958181
Position Surface form Disambiguated ID Type / Status
Subject Moni Naor E195495 entity
Predicate coAuthor P398 FINISHED
Object Eyal Kushilevitz E414312 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: Eyal Kushilevitz | Statement: [Moni Naor, coAuthor, Eyal Kushilevitz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eyal Kushilevitz
Context triple: [Moni Naor, coAuthor, Eyal Kushilevitz]
  • A. Eyal Kushilevitz chosen
    Eyal Kushilevitz is an Israeli computer scientist known for his influential work in cryptography, communication complexity, and theoretical computer science.
  • B. Noga Alon
    Noga Alon is an Israeli mathematician renowned for his influential work in combinatorics, graph theory, and theoretical computer science.
  • C. Moni Naor
    Moni Naor is an Israeli computer scientist renowned for his foundational contributions to cryptography and theoretical computer science.
  • D. Oded Goldreich
    Oded Goldreich is an Israeli computer scientist renowned for his foundational contributions to cryptography, computational complexity, and the theory of pseudorandomness.
  • E. Omer Reingold
    Omer Reingold is a prominent theoretical computer scientist known for his influential work in computational complexity and cryptography, including a landmark log-space algorithm for undirected graph connectivity.
  • 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_69ca82eaaa008190a54fa1a9f954b9ad completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb6cec7dc8190bb7e43c82a317707 completed April 2, 2026, 12:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69d281e1eb848190b898e36ec9821228 completed April 5, 2026, 3:38 p.m.
Created at: March 30, 2026, 8:46 p.m.