Triple

T15841720
Position Surface form Disambiguated ID Type / Status
Subject Kockums AB E384116 entity
Predicate locatedIn P40 FINISHED
Object Karlskrona E321383 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: Karlskrona | Statement: [Kockums AB, locatedIn, Karlskrona]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karlskrona
Context triple: [Kockums AB, locatedIn, Karlskrona]
  • A. Karlskrona chosen
    Karlskrona is a historic Swedish coastal city and naval base known for its well-preserved maritime architecture and UNESCO-listed naval port.
  • B. Karlsborg
    Karlsborg is a small Swedish locality best known for the historic Karlsborg Fortress on the shores of Lake Vättern.
  • C. Kalmar
    Kalmar is a historic coastal city in southeastern Sweden known for its medieval castle, role in the Kalmar Union, and connection to the island of Öland.
  • D. Kristianstad
    Kristianstad is a historic city in southern Sweden known for its well-preserved Renaissance architecture and proximity to the wetlands of the Kristianstad Vattenrike Biosphere Reserve.
  • E. Visby
    Visby is a well-preserved medieval Hanseatic town on the Swedish island of Gotland, renowned for its historic city wall and UNESCO World Heritage status.
  • 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_69d86da34c888190976e06c4019d415a completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e142e764088190afba6c5c1acf8199 completed April 16, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b31b3b4819095d0c24ee471e2a9 completed May 10, 2026, 11:56 p.m.
Created at: April 10, 2026, 4:50 a.m.