Triple

T19780412
Position Surface form Disambiguated ID Type / Status
Subject D25 E475114 entity
Predicate connectsArea P2564 FINISHED
Object Lika interior 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: Lika interior | Statement: [D25, connectsArea, Lika interior]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lika interior
Context triple: [D25, connectsArea, Lika interior]
  • A. Lika chosen
    Lika is a mountainous, sparsely populated historical region in central Croatia known for its karst landscapes, forests, and national parks such as Plitvice Lakes.
  • B. Laukaa
    Laukaa is a municipality in Central Finland known for its lakes, rural landscapes, and proximity to the city of Jyväskylä.
  • C. Lukiiko
    Lukiiko is the traditional legislative council of the Kingdom of Buganda, serving as its main representative and advisory assembly.
  • D. Doma
    Doma is a local government area and town in Nasarawa State, central Nigeria, known for its agrarian communities and proximity to the state capital, Lafia.
  • E. الحجرات
    الحجرات هي سورة مدنية في القرآن الكريم تُعنى بآداب التعامل الاجتماعي وضبط السلوك بين المسلمين.
  • 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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65382ff308190832800dd60675f7a completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:49 p.m.