Triple

T17266549
Position Surface form Disambiguated ID Type / Status
Subject Sha'ar Shechem E419141 entity
Predicate hasHebrewName P1435 FINISHED
Object שער שכם
שער שכם הוא אחד משערי העיר העתיקה בירושלים, מהכניסות המרכזיות והסואנות ביותר המובילות אל הרובע המוסלמי ושוקיו.
 E1260025 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: שער שכם | Statement: [Sha'ar Shechem, hasHebrewName, שער שכם]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: שער שכם
Context triple: [Sha'ar Shechem, hasHebrewName, שער שכם]
  • A. שער מרים
    שער מרים הוא אחד משערי העיר העתיקה בירושלים, הפונה להר הזיתים ומשמש כניסה מרכזית לרובע המוסלמי.
  • B. Sha'ar HaBarzel
    Sha'ar HaBarzel is the Hebrew name for the Iron Gate, a historic entrance associated with Jerusalem’s Old City.
  • C. Shaar HaKeniah
    Shaar HaKeniah is a section of the classic Jewish ethical work Chovot HaLevavot that focuses on the virtue and practice of humility.
  • D. רמת השרון
    רמת השרון היא עיר במרכז ישראל, השוכנת מצפון לתל אביב ונחשבת לעיר מבוססת ואיכותית עם רמת חיים גבוהה.
  • E. Shaar Perishut
    Shaar Perishut is a section of the medieval Jewish ethical work Chovot HaLevavot that focuses on the spiritual value of asceticism and detachment from worldly excess.
  • 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: שער שכם
Triple: [Sha'ar Shechem, hasHebrewName, שער שכם]
Generated description
שער שכם הוא אחד משערי העיר העתיקה בירושלים, מהכניסות המרכזיות והסואנות ביותר המובילות אל הרובע המוסלמי ושוקיו.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: שער שכם
Target entity description: שער שכם הוא אחד משערי העיר העתיקה בירושלים, מהכניסות המרכזיות והסואנות ביותר המובילות אל הרובע המוסלמי ושוקיו.
  • A. שער מרים
    שער מרים הוא אחד משערי העיר העתיקה בירושלים, הפונה להר הזיתים ומשמש כניסה מרכזית לרובע המוסלמי.
  • B. Sha'ar HaBarzel
    Sha'ar HaBarzel is the Hebrew name for the Iron Gate, a historic entrance associated with Jerusalem’s Old City.
  • C. Shaar HaKeniah
    Shaar HaKeniah is a section of the classic Jewish ethical work Chovot HaLevavot that focuses on the virtue and practice of humility.
  • D. רמת השרון
    רמת השרון היא עיר במרכז ישראל, השוכנת מצפון לתל אביב ונחשבת לעיר מבוססת ואיכותית עם רמת חיים גבוהה.
  • E. Shaar Perishut
    Shaar Perishut is a section of the medieval Jewish ethical work Chovot HaLevavot that focuses on the spiritual value of asceticism and detachment from worldly excess.
  • 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_69d886d9ab108190b70edd8d17aa1204 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42f45bf608190bcb48783d0d6fb85 completed April 19, 2026, 1:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01794641648190a5db87ecb359c17a completed May 11, 2026, 6:37 a.m.
NEDg Description generation batch_6a017abddcc48190872f77b62ac9896e completed May 11, 2026, 6:44 a.m.
NED2 Entity disambiguation (via description) batch_6a017b7e72908190913215717fb04b0f completed May 11, 2026, 6:47 a.m.
Created at: April 10, 2026, 5:40 a.m.