Triple

T21511630
Position Surface form Disambiguated ID Type / Status
Subject أمانة العاصمة E530737 entity
Predicate تضم P1393 FINISHED
Object الجامع الكبير في صنعاء NE NERFINISHED

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: الجامع الكبير في صنعاء | Statement: [أمانة العاصمة, تضم, الجامع الكبير في صنعاء]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: الجامع الكبير في صنعاء
Context triple: [أمانة العاصمة, تضم, الجامع الكبير في صنعاء]
  • A. Great Mosque of Sanaʽa chosen
    The Great Mosque of Sanaʽa is one of the oldest and most significant mosques in the Islamic world, renowned for its early Islamic architecture and central religious role in Yemen’s capital.
  • B. جامع عقبة بن نافع
    جامع عقبة بن نافع هو أحد أقدم وأهم المساجد في العالم الإسلامي، يقع في مدينة القيروان بتونس ويُعد مركزاً تاريخياً للعلم والدعوة في المغرب العربي.
  • C. الجامع الكبير
    الجامع الكبير هو مسجد تاريخي عريق في مدينة الجزائر يُعد من أقدم وأهم المعالم الإسلامية في البلاد.
  • D. Academy of the Arabic Language in Sana'a
    The Academy of the Arabic Language in Sana'a is a Yemeni scholarly institution dedicated to the study, preservation, and regulation of the Arabic language and its usage.
  • E. الجامع العمري
    الجامع العمري هو مسجد تاريخي عريق يقع في البلدة القديمة بمدينة غزة ويُعد من أقدم وأهم معالمها الدينية والمعمارية.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c45c81f08190a6b8bbb70a45aae7 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea863b18819080e3ff249b10ec28 completed April 23, 2026, 9:46 a.m.
Created at: April 16, 2026, 6:25 p.m.