Triple

T36589894
Position Surface form Disambiguated ID Type / Status
Subject יצחק הרצוג E902638 entity
Predicate אם P185904 FINISHED
Object אורה הרצוג
אורה הרצוג הייתה אשת ציבור ישראלית, פעילה חברתית ונשיאת ארגון ויצ"ו ישראל, שנודעה גם כאשתו של הנשיא חיים הרצוג ואםו של נשיא המדינה יצחק הרצוג.
 E2191133 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: אורה הרצוג | Statement: [יצחק הרצוג, אם, אורה הרצוג]
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: אורה הרצוג
Triple: [יצחק הרצוג, אם, אורה הרצוג]
Generated description
אורה הרצוג הייתה אשת ציבור ישראלית, פעילה חברתית ונשיאת ארגון ויצ"ו ישראל, שנודעה גם כאשתו של הנשיא חיים הרצוג ואםו של נשיא המדינה יצחק הרצוג.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: אם
Context triple: [יצחק הרצוג, אם, אורה הרצוג]
  • A. عم
    Indicates a familial relationship where one entity is the paternal uncle (father’s brother) of another entity.
  • B. isin
    Indicates that one entity is contained within, or is a member of, another entity or set.
  • C. by
    Indicates that an action is performed, caused, or authored through the agency, means, or proximity of a specified entity.
  • D. uso
    Indicates that one entity uses, employs, or makes use of another entity for some purpose or function.
  • E. is
    Indicates that two entities are equivalent, share an attribute, or stand in a specified state or relation to each other.
  • F. None of above. chosen

Provenance (7 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_69f76e6592e88190bac4eb00a46e9df9 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69f7c371931c8190afb1d4dd5157f92c completed May 3, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_6a39f91c8dd481909159e901fe880c77 completed June 23, 2026, 3:10 a.m.
NEDg Description generation batch_6a39f994d03c8190ab5749c75dc63a55 completed June 23, 2026, 3:12 a.m.
NED2 Entity disambiguation (via description) batch_6a39fb5d5ce08190be8f234468af3698 completed June 23, 2026, 3:19 a.m.
PD Predicate disambiguation batch_69f7c1baf25c8190a78dd54a400d2c50 completed May 3, 2026, 9:44 p.m.
PDg Predicate description generation batch_69f7c3705b5c81908c84004543a71c07 completed May 3, 2026, 9:51 p.m.
Created at: May 3, 2026, 4:11 p.m.