Triple

T9384256
Position Surface form Disambiguated ID Type / Status
Subject לֵאָה E225864 entity
Predicate tribeAncestorOf P46213 FINISHED
Object שבט לוי
שבט לוי הוא אחד משבטי ישראל, המוכר כשבט הכהונה והשירות במקדש, שממנו יצאו הכוהנים והלויים המופקדים על עבודת הקודש.
 E797114 NE FINISHED

How this triple was built (4 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: שבט לוי | Statement: [לֵאָה, tribeAncestorOf, שבט לוי]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: שבט לוי
Context triple: [לֵאָה, tribeAncestorOf, שבט לוי]
  • A. Shlomo
    Shlomo is the Hebrew name for King Solomon, the biblical monarch renowned for his wisdom, wealth, and the construction of the First Temple in Jerusalem.
  • B. Hagai Levi
    Hagai Levi is an Israeli television creator, writer, and director best known for originating the drama series BeTipul, which was adapted internationally as In Treatment.
  • C. Dovid
    Dovid is a masculine given name of Hebrew origin, commonly used in Jewish communities as a variant of David.
  • D. Yigal Shiloh
    Yigal Shiloh was an Israeli archaeologist best known for his influential excavations in Jerusalem and his contributions to the study of ancient Israelite urbanism and material culture.
  • E. Shmuel
    Shmuel is the Hebrew form of the biblical name Samuel, commonly used in Jewish religious and cultural contexts.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: שבט לוי
Triple: [לֵאָה, tribeAncestorOf, שבט לוי]
Generated description
שבט לוי הוא אחד משבטי ישראל, המוכר כשבט הכהונה והשירות במקדש, שממנו יצאו הכוהנים והלויים המופקדים על עבודת הקודש.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: שבט לוי
Target entity description: שבט לוי הוא אחד משבטי ישראל, המוכר כשבט הכהונה והשירות במקדש, שממנו יצאו הכוהנים והלויים המופקדים על עבודת הקודש.
  • A. Shlomo
    Shlomo is the Hebrew name for King Solomon, the biblical monarch renowned for his wisdom, wealth, and the construction of the First Temple in Jerusalem.
  • B. Hagai Levi
    Hagai Levi is an Israeli television creator, writer, and director best known for originating the drama series BeTipul, which was adapted internationally as In Treatment.
  • C. Dovid
    Dovid is a masculine given name of Hebrew origin, commonly used in Jewish communities as a variant of David.
  • D. Yigal Shiloh
    Yigal Shiloh was an Israeli archaeologist best known for his influential excavations in Jerusalem and his contributions to the study of ancient Israelite urbanism and material culture.
  • E. Shmuel
    Shmuel is the Hebrew form of the biblical name Samuel, commonly used in Jewish religious and cultural contexts.
  • F. None of above. chosen

Provenance (5 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_69ca842e9dcc8190a264119e683cfe04 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd50c23e7881908112597a1771afa5 completed April 1, 2026, 5:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1078fbc8c8190ac27c5cb27793a9a completed April 4, 2026, 12:43 p.m.
NEDg Description generation batch_69d108466fb481909682fcaac354b312 completed April 4, 2026, 12:47 p.m.
NED2 Entity disambiguation (via description) batch_69d108bab8c881909748ffbb4b23f4ba completed April 4, 2026, 12:48 p.m.
Created at: March 30, 2026, 7:44 p.m.