Triple

T12540300
Position Surface form Disambiguated ID Type / Status
Subject Tama Campus E299817 entity
Predicate name P16 FINISHED
Object Tama Campus E299817 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: Tama Campus | Statement: [Tama Campus, name, Tama Campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tama Campus
Context triple: [Tama Campus, name, Tama Campus]
  • A. Tama Campus chosen
    Tama Campus is one of Hosei University’s main campuses, located in the Tama area of Tokyo and housing several of the university’s faculties and facilities.
  • B. Kikuyu Campus
    Kikuyu Campus is one of the constituent campuses of the University of Nairobi, located in Kikuyu and known primarily for hosting education and related academic programs.
  • C. Bundoora campus
    Bundoora campus is the primary and largest campus of La Trobe University, located in the Melbourne suburb of Bundoora, Australia.
  • D. Corio campus
    Corio campus is the main and historic campus of Geelong Grammar School, located in Corio near Geelong, Victoria, Australia.
  • E. Laucala Campus
    Laucala Campus is the primary and largest campus of the University of the South Pacific, located in Suva, Fiji, serving as the university’s main academic and administrative hub.
  • 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_69d6ada707008190aaec1238117c9379 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9546fc620819093335988dbab3256 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6557cb180819083ee10708320199e completed May 2, 2026, 7:50 p.m.
Created at: April 8, 2026, 9:57 p.m.