Triple

T21084243
Position Surface form Disambiguated ID Type / Status
Subject Iranian universities E519444 entity
Predicate includeInstitution P3814 FINISHED
Object Razi University 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: Razi University | Statement: [Iranian universities, includeInstitution, Razi University]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Razi University
Context triple: [Iranian universities, includeInstitution, Razi University]
  • A. Razi University chosen
    Razi University is a public higher education and research institution located in Kermanshah, Iran.
  • B. Yazd University
    Yazd University is a public higher education and research institution located in the city of Yazd, Iran.
  • C. Shiraz University of Medical Sciences
    Shiraz University of Medical Sciences is a major public medical university and healthcare education center located in the city of Shiraz in southern Iran.
  • D. Shahrekord University
    Shahrekord University is a public higher education institution located in the city of Shahrekord in western Iran, offering a range of undergraduate and graduate programs.
  • E. Bu-Ali Sina University
    Bu-Ali Sina University is a public higher education institution in Hamadan, Iran, known for its programs in sciences, engineering, and humanities.
  • 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_69e0b507dd9081908fb8bfcbef4c8b46 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e70948704481908b8b75a2ecc42bb6 completed April 21, 2026, 5:21 a.m.
Created at: April 16, 2026, 2:49 p.m.