Triple

T3882269
Position Surface form Disambiguated ID Type / Status
Subject Akershus E92851 entity
Predicate predecessor P97 FINISHED
Object Akershus len E92851 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: Akershus len | Statement: [Akershus, predecessor, Akershus len]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akershus len
Context triple: [Akershus, predecessor, Akershus len]
  • A. Akershus chosen
    Akershus is a historical county in southeastern Norway that encompassed areas around the capital Oslo and played a key role in the region’s administrative and military history.
  • B. Akershus Fortress
    Akershus Fortress is a historic medieval castle and former royal residence that has served as a key military stronghold and national symbol in Norway’s capital.
  • C. Akershus Royal Banquet Hall
    Akershus Royal Banquet Hall is a medieval castle–themed character dining restaurant in EPCOT’s World Showcase, best known for its Disney Princess meals.
  • D. Akersneset
    Akersneset is a headland in central Oslo, Norway, forming part of the waterfront area that includes the historic Akershus Fortress.
  • E. St. Hanshaugen
    St. Hanshaugen is a central borough of Oslo, Norway, known for its large hillside park and vibrant urban residential areas.
  • 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_69aed9697de0819087c2559295ff3d12 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeec8e8b3481909617ca0e37f8a6d4 completed March 9, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b512594fa081909ba2afad11f6ea59 completed March 14, 2026, 7:46 a.m.
Created at: March 9, 2026, 3:20 p.m.