Triple

T22874854
Position Surface form Disambiguated ID Type / Status
Subject Al-Azhar Park E567295 entity
Predicate namedAfter P63 FINISHED
Object Al-Azhar 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: Al-Azhar | Statement: [Al-Azhar Park, namedAfter, Al-Azhar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Al-Azhar
Context triple: [Al-Azhar Park, namedAfter, Al-Azhar]
  • A. Al-Azhar University chosen
    Al-Azhar University is one of the world’s oldest and most influential centers of Islamic learning and higher education, located in Cairo, Egypt.
  • B. Al-Qarawiyyin University
    Al-Qarawiyyin University is a historic center of Islamic learning in Fez, Morocco, often regarded as one of the oldest continuously operating universities in the world.
  • C. جامع علاء الدين
    جامع علاء الدين هو مسجد تاريخي كبير يقع على تلة علاء الدين في مدينة قونية بتركيا ويُعد من أقدم وأهم مساجدها السلجوقية.
  • D. Luxor University
    Luxor University is a public higher education institution in Luxor, Egypt, offering a range of academic programs and research activities serving Upper Egypt.
  • E. Damietta University
    Damietta University is a public higher education institution in Damietta, Egypt, offering a range of undergraduate and postgraduate programs across multiple disciplines.
  • 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_69e24589d8348190b96422d13a678bc1 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17f57a1ec8190b8c6a0080d97a2a2 completed April 29, 2026, 3:47 a.m.
Created at: April 17, 2026, 3:39 p.m.