Triple

T9443147
Position Surface form Disambiguated ID Type / Status
Subject Treading Air E227697 entity
Predicate author P4 FINISHED
Object Jaan Kross E45398 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: Jaan Kross | Statement: [Treading Air, author, Jaan Kross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jaan Kross
Context triple: [Treading Air, author, Jaan Kross]
  • A. Jaan Kross chosen
    Jaan Kross was a prominent Estonian writer and poet, best known for his historical novels that explore Estonia’s past and its struggles under foreign rule.
  • B. Edgar Savisaar
    Edgar Savisaar is an Estonian politician and founding figure of the post-Soviet Estonian state, known for leading the Popular Front of Estonia and serving in several top government roles.
  • C. Toomas Luman
    Toomas Luman is an Estonian businessman and influential economic leader, known particularly for his long-term role in shaping Estonia’s business and construction sectors.
  • D. Toomas Vint
    Toomas Vint is an Estonian writer and painter known for his surreal, introspective prose and distinctive, often metaphysical visual art.
  • E. Jaan Tallinn
    Jaan Tallinn is an Estonian computer programmer, investor, and co-founder of Skype and Kazaa, known for his work in technology entrepreneurship and AI safety advocacy.
  • 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_69ca843884488190ad6cbe0153088234 completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd7f3171248190b92ab990371e63f5 completed April 1, 2026, 8:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1bca63c3c819084aec1c0bb962ffe completed April 5, 2026, 1:36 a.m.
Created at: March 30, 2026, 7:51 p.m.