Triple

T10666286
Position Surface form Disambiguated ID Type / Status
Subject 2017 Winter Universiade E251364 entity
Predicate mascot P52 FINISHED
Object Sunkar
Sunkar is the falcon-themed mascot created for the 2017 Winter Universiade held in Almaty, Kazakhstan.
 E876736 NE FINISHED

How this triple was built (4 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: Sunkar | Statement: [2017 Winter Universiade, mascot, Sunkar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sunkar
Context triple: [2017 Winter Universiade, mascot, Sunkar]
  • A. Nakoruru
    Nakoruru is a popular Samurai Shodown character known as a nature-loving Ainu shrine maiden who fights alongside her hawk and wolf companions.
  • B. Sakaar
    Sakaar is a chaotic, trash-covered planet ruled by the Grandmaster in the Marvel Cinematic Universe, known for its gladiatorial contests and bizarre cosmic detritus.
  • C. Susuman
    Susuman is a small mining town in Russia's Magadan Oblast, located in the remote Russian Far East.
  • D. Sirokakara
    Sirokakara is a small settlement located on Choiseul Island in the Solomon Islands.
  • E. Shinkiari
    Shinkiari is a town in Pakistan’s Khyber Pakhtunkhwa province, known for its agricultural surroundings and its location along the Karakoram Highway near Mansehra.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sunkar
Triple: [2017 Winter Universiade, mascot, Sunkar]
Generated description
Sunkar is the falcon-themed mascot created for the 2017 Winter Universiade held in Almaty, Kazakhstan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sunkar
Target entity description: Sunkar is the falcon-themed mascot created for the 2017 Winter Universiade held in Almaty, Kazakhstan.
  • A. Nakoruru
    Nakoruru is a popular Samurai Shodown character known as a nature-loving Ainu shrine maiden who fights alongside her hawk and wolf companions.
  • B. Sakaar
    Sakaar is a chaotic, trash-covered planet ruled by the Grandmaster in the Marvel Cinematic Universe, known for its gladiatorial contests and bizarre cosmic detritus.
  • C. Susuman
    Susuman is a small mining town in Russia's Magadan Oblast, located in the remote Russian Far East.
  • D. Sirokakara
    Sirokakara is a small settlement located on Choiseul Island in the Solomon Islands.
  • E. Shinkiari
    Shinkiari is a town in Pakistan’s Khyber Pakhtunkhwa province, known for its agricultural surroundings and its location along the Karakoram Highway near Mansehra.
  • F. None of above. chosen

Provenance (5 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_69d6aa5b0d2881909584b20efc5877f0 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6f31f87748190bb44db8afa901763 completed April 9, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69d97a9566e08190a92b49ce73963078 completed April 10, 2026, 10:32 p.m.
NEDg Description generation batch_69d97cc2b66c8190909a23927fbe3af5 completed April 10, 2026, 10:42 p.m.
NED2 Entity disambiguation (via description) batch_69d97e189800819087bf6af15b2370a2 completed April 10, 2026, 10:47 p.m.
Created at: April 8, 2026, 9:08 p.m.