Triple

T19970518
Position Surface form Disambiguated ID Type / Status
Subject וַשְׁתִּי E480058 entity
Predicate canonicalBook P29317 FINISHED
Object Ketuvim 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: Ketuvim | Statement: [וַשְׁתִּי, canonicalBook, Ketuvim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ketuvim
Context triple: [וַשְׁתִּי, canonicalBook, Ketuvim]
  • A. Ketuvim chosen
    Ketuvim is the third section of the Hebrew Bible, comprising a diverse collection of poetic, wisdom, and historical writings central to Jewish scripture.
  • B. Neviim
    Neviim is the section of the Hebrew Bible that contains the prophetic books and historical narratives of the prophets in Judaism.
  • C. Commentary on Ketuvim
    Commentary on Ketuvim is Malbim’s detailed exegetical work on the Writings section of the Hebrew Bible, known for its linguistic precision and emphasis on the uniqueness of biblical language.
  • D. Sefer ha-Te'amim
    Sefer ha-Te'amim is a medieval Hebrew work by Abraham ibn Ezra that explores the grammatical, exegetical, and often philosophical reasons (“ta‘amim”) behind biblical language and interpretation.
  • E. Sefer Zeraim
    Sefer Zeraim is the section of Maimonides’ Mishneh Torah that codifies Jewish agricultural laws and related commandments.
  • 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65bc89b508190879d29bef546aac8 completed April 20, 2026, 5 p.m.
Created at: April 10, 2026, 1:54 p.m.