Triple

T4664078
Position Surface form Disambiguated ID Type / Status
Subject Sifre Devarim E102802 entity
Predicate relatedWork P37 FINISHED
Object Sifre Bamidbar E226935 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: Sifre Bamidbar | Statement: [Sifre Devarim, relatedWork, Sifre Bamidbar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sifre Bamidbar
Context triple: [Sifre Devarim, relatedWork, Sifre Bamidbar]
  • A. Sifre Bamidbar chosen
    Sifre Bamidbar is a tannaitic midrashic work offering halakhic and aggadic commentary on the biblical Book of Numbers.
  • B. Sifra di-Tsni’uta
    Sifra di-Tsni’uta is a brief but highly influential mystical treatise within the Zoharic corpus that offers dense, symbolic teachings central to later Kabbalistic thought.
  • C. The Book of Numbers
    The Book of Numbers is a popular mathematics book that explores the properties, patterns, and curiosities of numbers in an accessible and engaging way.
  • D. Sarei HaMeah
    Sarei HaMeah is a significant Hebrew work by Rabbi Yehuda Leib Maimon that profiles and analyzes one hundred prominent rabbinic figures.
  • E. Zohar Manna
    Zohar Manna was a pioneering computer scientist known for his foundational work in mathematical logic, program verification, and the formal methods of software correctness.
  • 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_69bd43d9cba4819086c1ab1c2d9d2133 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd633aeba88190a8329ed022d685b6 completed March 20, 2026, 3:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69be03803a948190b6dc2a03bb9cdc93 completed March 21, 2026, 2:33 a.m.
Created at: March 20, 2026, 1:15 p.m.