Triple

T1575862
Position Surface form Disambiguated ID Type / Status
Subject Halvdan Koht E33648 entity
Predicate employer P7 FINISHED
Object Royal Frederick University E43588 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: Royal Frederick University | Statement: [Halvdan Koht, employer, Royal Frederick University]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Royal Frederick University
Context triple: [Halvdan Koht, employer, Royal Frederick University]
  • A. Royal Frederick University chosen
    Royal Frederick University was the former name of the University of Oslo, Norway’s oldest and most prestigious university.
  • B. Strathmore University
    Strathmore University is a leading private university in Kenya known for its strong programs in business, information technology, and law.
  • C. MacEwan University
    MacEwan University is a public undergraduate-focused university located in downtown Edmonton, Alberta, Canada.
  • D. Franeker University
    Franeker University was an early modern Dutch university in the city of Franeker, Friesland, known as a center of Reformed and humanist scholarship.
  • E. United College
    United College is an affiliated college of the University of Waterloo that provides academic programs, residence, and community-focused learning experiences for students.
  • 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_69a885f27a4c8190a4622252cdf54c00 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908d2cffc819090f3d5cbebae3307 completed March 5, 2026, 4:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad402b44688190b02e6d146f009854 completed March 8, 2026, 9:23 a.m.
Created at: March 4, 2026, 7:27 p.m.