Triple

T1824644
Position Surface form Disambiguated ID Type / Status
Subject Kartlians E40623 entity
Predicate relatedGroup P37 FINISHED
Object Svans E9015 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: Svans | Statement: [Kartlians, relatedGroup, Svans]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Svans
Context triple: [Kartlians, relatedGroup, Svans]
  • A. Svans chosen
    Svans are a distinct subethnic group of Georgians known for their unique Svan language, highland culture, and traditional communities in the Svaneti region of the Caucasus.
  • B. Byrde
    Byrde is an archaic or variant spelling of the word "bird," historically used in Middle and Early Modern English texts.
  • C. Nanooks
    Nanooks is the nickname for the University of Alaska Fairbanks athletic teams, representing the school in NCAA competition.
  • D. Orcines
    Orcines is a commune in central France’s Puy-de-Dôme department, known for its proximity to the Chaîne des Puys volcanic range.
  • E. Sparviero
    Sparviero is the Italian nickname for the Savoia-Marchetti SM.79, a World War II-era three-engined medium bomber and torpedo bomber used prominently by the Italian Air Force.
  • 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_69a8864644bc8190b2358ab897194ac1 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb0003d308190a024f8c03c5f5dad completed March 7, 2026, 4:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69adc9af6d3c8190a9047d06f38f210d completed March 8, 2026, 7:10 p.m.
Created at: March 4, 2026, 7:32 p.m.