Triple

T2024805
Position Surface form Disambiguated ID Type / Status
Subject Haggadah E44182 entity
Predicate relatedText P8272 FINISHED
Object Torah E7794 NE FINISHED

How this triple was built (3 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: Torah | Statement: [Haggadah, relatedText, Torah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Torah
Context triple: [Haggadah, relatedText, Torah]
  • A. Torah chosen
    The Torah is the central and most sacred text of Judaism, comprising the foundational five books that outline Jewish law, teachings, and early history.
  • B. Tanakh
    The Tanakh is the canonical collection of Hebrew scriptures that forms the foundational religious text of Judaism, encompassing the Torah (Law), Nevi'im (Prophets), and Ketuvim (Writings).
  • C. Talmud
    The Talmud is a central Jewish religious text comprising rabbinic discussions, legal rulings, and interpretations of the Hebrew Bible that form the foundation of traditional Jewish law and theology.
  • D. Sefer HaMadda
    Sefer HaMadda is the opening book of Maimonides’ Mishneh Torah, laying out foundational principles of Jewish belief, ethics, and religious practice.
  • E. Arba’ah Turim
    Arba’ah Turim is a foundational 14th-century Jewish legal code by Rabbi Jacob ben Asher that systematically organizes and clarifies halakhic rulings for practical religious life.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relatedText
Context triple: [Haggadah, relatedText, Torah]
  • A. relatedTo
    Indicates a general, non-specific relationship or association exists between two entities.
  • B. relatedField
    Indicates that one field, topic, or area of study is connected or relevant to another in subject matter or application.
  • C. associatedWithText chosen
    Indicates that an entity has a contextual or semantic connection to a specific piece of text.
  • D. relatedBlock
    Indicates that one block is associated with or connected to another block in some relevant way.
  • E. relatedRFC
    Indicates that one resource or specification is connected or associated with another through a shared or relevant RFC (Request for Comments) document.
  • F. None of above.

Provenance (4 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_69a8891201bc8190aca837be6de41579 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb8f2cd5c8190b19da6f6aa2001d6 completed March 7, 2026, 5:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae304aa0888190a725234d8e527ac5 completed March 9, 2026, 2:28 a.m.
PD Predicate disambiguation batch_69abb7a656248190ac2ced196b35bc6b completed March 7, 2026, 5:29 a.m.
Created at: March 4, 2026, 7:38 p.m.