Triple

T18949143
Position Surface form Disambiguated ID Type / Status
Subject Shenzhen University E463597 entity
Predicate hasCampus P116 FINISHED
Object Xili Campus 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: Xili Campus | Statement: [Shenzhen University, hasCampus, Xili Campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Xili Campus
Context triple: [Shenzhen University, hasCampus, Xili Campus]
  • A. Xili campus chosen
    Xili campus is one of the main campuses of Shenzhen University, located in the Xili area of Shenzhen, China.
  • B. Sipailou Campus
    Sipailou Campus is the historic main campus of Southeast University in Nanjing, China, known for its traditional architecture and central urban location.
  • C. Fahuazhen Campus
    Fahuazhen Campus is one of Shanghai Jiao Tong University’s urban campuses, located in central Shanghai and primarily hosting humanities and social science disciplines.
  • D. Dadu Campus
    Dadu Campus is a regional campus of the University of Sindh that provides higher education services to students in and around the Dadu district of Pakistan.
  • E. Ekehuan Campus
    Ekehuan Campus is one of the main campuses of the University of Benin in Nigeria, known primarily for housing arts, education, and related academic programs.
  • 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_69d8dcfec90481909e926be9767e5779 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d541ef18819080b2e253dd23835d completed April 20, 2026, 7:26 a.m.
Created at: April 10, 2026, noon