Triple

T23419351
Position Surface form Disambiguated ID Type / Status
Subject KSU E560604 entity
Predicate hasCampus P116 FINISHED
Object Kent 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: Kent Campus | Statement: [KSU, hasCampus, Kent Campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kent Campus
Context triple: [KSU, hasCampus, Kent Campus]
  • A. Kent Campus chosen
    Kent Campus is the main campus of Kent State University in Kent, Ohio, serving as the central hub for its academic, administrative, and student life activities.
  • B. Severn Campus
    Severn Campus is a University of Worcester site focused on health, science, and professional education facilities along the River Severn in Worcester, England.
  • C. Keele
    Keele is a village in Staffordshire, England, best known as the home of Keele University and its extensive rural campus.
  • D. Chesterfield campus
    Chesterfield campus is a University of Derby site in Chesterfield that provides higher education facilities and courses serving students in the town and surrounding region.
  • E. Talbot Campus
    Talbot Campus is Bournemouth University's main campus, housing the majority of its academic faculties, student facilities, and media and technology centers in Poole, Dorset, England.
  • 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_69e2454cb1108190ab21ada5411a7146 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a54489d48190b2b2c29701851765 completed April 29, 2026, 6:29 a.m.
Created at: April 17, 2026, 5:44 p.m.