Triple

T9743821
Position Surface form Disambiguated ID Type / Status
Subject University of Madras E236256 entity
Predicate hasCampus P116 FINISHED
Object Chetpet campus E236256 NE FINISHED

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: Chetpet campus | Statement: [University of Madras, hasCampus, Chetpet campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chetpet campus
Context triple: [University of Madras, hasCampus, Chetpet campus]
  • A. Chetpet campus chosen
    Chetpet campus is one of the constituent campuses of the University of Madras located in the Chetpet area of Chennai, India.
  • B. Anam Campus
    Anam Campus is the main and largest campus of Korea University, located in the Anam-dong area of Seoul.
  • C. Choba campus
    Choba campus is the main campus of the University of Port Harcourt in Rivers State, Nigeria, housing most of its academic, administrative, and student facilities.
  • D. Tura campus
    Tura campus is a regional campus of North-Eastern Hill University located in Tura, Meghalaya, serving as a higher education and research hub for the western part of the state.
  • E. Ganesha Campus
    Ganesha Campus is the main and historic campus of Institut Teknologi Bandung, located in central Bandung, Indonesia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca84d3e24481908a476e2231123cf9 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9f2e5bb081908047e3bf5fe3991c completed April 1, 2026, 10:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1affb761881908dde9a4f028c32f6 completed April 5, 2026, 12:42 a.m.
Created at: March 30, 2026, 8:23 p.m.