Triple

T18223151
Position Surface form Disambiguated ID Type / Status
Subject Armen Sarkissian E436354 entity
Predicate workLocation P7 FINISHED
Object Yerevan 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: Yerevan | Statement: [Armen Sarkissian, workLocation, Yerevan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yerevan
Context triple: [Armen Sarkissian, workLocation, Yerevan]
  • A. Yerevan, Armenia chosen
    Yerevan, Armenia is the capital and largest city of Armenia, known for its ancient history, distinctive pink tuff stone architecture, and location in the Ararat Valley near Mount Ararat.
  • B. Gyumri
    Gyumri is Armenia’s second-largest city, known for its rich cultural heritage, historic architecture, and resilience following the 1988 Spitak earthquake.
  • C. Dilijan
    Dilijan is a picturesque spa town in Armenia’s Tavush Province, known for its forested landscapes, traditional architecture, and proximity to Dilijan National Park.
  • D. Ararat Yerevan
    Ararat Yerevan is a prominent Armenian football club from Yerevan, historically known as one of the leading teams in Soviet and Armenian football.
  • E. Ijevan
    Ijevan is a town in northeastern Armenia known as the administrative center of the Tavush Province and noted for its surrounding forests, wine production, and historical sites.
  • 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_69d8b9103a8081908bbb0836fef10efd completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e47d9b348190897d5a1e70b39ec5 completed April 19, 2026, 2:19 p.m.
Created at: April 10, 2026, 10:32 a.m.