Triple

T17488416
Position Surface form Disambiguated ID Type / Status
Subject Academe E425834 entity
Predicate title P38 FINISHED
Object Academe 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: Academe | Statement: [Academe, title, Academe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Academe
Context triple: [Academe, title, Academe]
  • A. Academe chosen
    Academe is a scholarly magazine published by the American Association of University Professors that focuses on issues in higher education, academic freedom, and faculty governance.
  • B. Académica
    Académica is a historic Portuguese sports club and football team from Coimbra, traditionally associated with the University of Coimbra and its student community.
  • C. Academic Acropolis
    Academic Acropolis is a nickname for the cluster of prominent academic institutions and campuses situated on the elevated terrain of Morningside Heights in New York City.
  • D. Akademikerne
    Akademikerne is a Danish confederation representing highly educated professionals and academics in matters of labor rights, wages, and working conditions.
  • E. Academy
    Academy is the ancient Athenian site that housed Plato’s philosophical school and became synonymous with institutions of higher learning.
  • 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_69d889dccf7481909264a1844a2e9100 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451d376708190a97804529174eaf2 completed April 19, 2026, 3:53 a.m.
Created at: April 10, 2026, 5:48 a.m.