Triple

T17383545
Position Surface form Disambiguated ID Type / Status
Subject שירות הביטחון הכללי E422629 entity
Predicate שם_נוסף P744 FINISHED
Object שין־בית
שין־בית הוא שירות הביטחון הכללי של מדינת ישראל, האחראי על ביטחון הפנים, סיכול טרור וריגול נגדי.
 E1266466 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: שין־בית | Statement: [שירות הביטחון הכללי, שם_נוסף, שין־בית]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: שין־בית
Context triple: [שירות הביטחון הכללי, שם_נוסף, שין־בית]
  • A. Kotel
    Kotel is a small historic town in eastern Bulgaria known for its role in the Bulgarian National Revival and its well-preserved traditional architecture.
  • B. Har HaBayit
    Har HaBayit is the Hebrew name for the Temple Mount in Jerusalem, a site of central religious and historical significance in Judaism, Christianity, and Islam.
  • C. Sha'ar Tzion
    Sha'ar Tzion is the Hebrew name for the historic Zion Gate in Jerusalem’s Old City walls, a key entrance near Mount Zion.
  • D. Beit HaNassi
    Beit HaNassi is the official residence and ceremonial home of the President of Israel, located in Jerusalem.
  • E. Beit El
    Beit El is an Israeli settlement in the central West Bank that serves as a key administrative and military hub for Israeli authorities in the area.
  • 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: שין־בית
Triple: [שירות הביטחון הכללי, שם_נוסף, שין־בית]
Generated description
שין־בית הוא שירות הביטחון הכללי של מדינת ישראל, האחראי על ביטחון הפנים, סיכול טרור וריגול נגדי.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: שין־בית
Target entity description: שין־בית הוא שירות הביטחון הכללי של מדינת ישראל, האחראי על ביטחון הפנים, סיכול טרור וריגול נגדי.
  • A. Kotel
    Kotel is a small historic town in eastern Bulgaria known for its role in the Bulgarian National Revival and its well-preserved traditional architecture.
  • B. Har HaBayit
    Har HaBayit is the Hebrew name for the Temple Mount in Jerusalem, a site of central religious and historical significance in Judaism, Christianity, and Islam.
  • C. Sha'ar Tzion
    Sha'ar Tzion is the Hebrew name for the historic Zion Gate in Jerusalem’s Old City walls, a key entrance near Mount Zion.
  • D. Beit HaNassi
    Beit HaNassi is the official residence and ceremonial home of the President of Israel, located in Jerusalem.
  • E. Beit El
    Beit El is an Israeli settlement in the central West Bank that serves as a key administrative and military hub for Israeli authorities in the area.
  • 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_69d889d6535c81908be333c01deaec4e completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a87d9948190986021f1fb5a4e00 completed April 19, 2026, 2:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a019ff72ca08190a5ea8a1ba6330728 completed May 11, 2026, 9:23 a.m.
NEDg Description generation batch_6a01a1887d408190baf6d68b17917c09 completed May 11, 2026, 9:29 a.m.
NED2 Entity disambiguation (via description) batch_6a01a2777c188190960046cb7c0b8404 completed May 11, 2026, 9:33 a.m.
Created at: April 10, 2026, 5:45 a.m.