Triple

T10429226
Position Surface form Disambiguated ID Type / Status
Subject Ski E245864 entity
Predicate formerCounty P1069 FINISHED
Object Akershus 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 | Statement: [Ski, formerCounty, Akershus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akershus
Context triple: [Ski, formerCounty, Akershus]
  • 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. Karljohansvern
    Karljohansvern is a historic former naval base and shipyard in Horten, Norway, now serving as a cultural heritage site with museums and maritime attractions.
  • D. Eidsvoll
    Eidsvoll is a historic Norwegian town best known as the site where Norway’s constitution was drafted and signed in 1814.
  • E. Royal Palace, Oslo
    The Royal Palace in Oslo is the official residence of the Norwegian monarch and a central symbol of Norway’s constitutional monarchy and national heritage.
  • 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_69d381bf3dc08190bf35a2643e4e8f22 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4ea4b4b5881908ae23f8efeea482b completed April 7, 2026, 11:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69d9987838ac8190a6ba09305fc27621 completed April 11, 2026, 12:40 a.m.
Created at: April 6, 2026, 12:13 p.m.