Triple

T13770569
Position Surface form Disambiguated ID Type / Status
Subject זבולון E330867 entity
Predicate אחיו P363 FINISHED
Object יוסף E443708 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: יוסף | Statement: [זבולון, אחיו, יוסף]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: יוסף
Context triple: [זבולון, אחיו, יוסף]
  • A. Yosef
    Yosef is a Hebrew given name of biblical origin, best known from the patriarch Joseph and widely used in Jewish communities.
  • B. יעקב
    יעקב הוא אחד מאבות האומה המקראיים, דמות מרכזית בספר בראשית ואבי שנים-עשר שבטי ישראל.
  • C. Yacob
    Yacob is the surname of Halimah Yacob, a prominent Singaporean politician and the country’s first female president.
  • D. Yehuda
    Yehuda is a Hebrew given name traditionally associated with the biblical tribe of Judah and commonly used in Jewish communities.
  • E. Joseph son of Jacob chosen
    Joseph son of Jacob is a central biblical figure known for his prophetic dreams, being sold into slavery by his brothers, and rising to become a powerful leader in Egypt who ultimately saves his family from famine.
  • 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_69d81c583b0081909e408a17db517a21 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0235aea881909ab4c721db081b00 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b8d28cc88190af46b86473af0a1c completed May 3, 2026, 9:06 p.m.
Created at: April 9, 2026, 10:10 p.m.