Triple

T23165727
Position Surface form Disambiguated ID Type / Status
Subject Kazushi Sakuraba E578706 entity
Predicate nickname P55 FINISHED
Object Saku
Saku is the nickname of Kazushi Sakuraba, a legendary Japanese mixed martial artist famed for his grappling skills and victories over multiple members of the Gracie family.
 E1572907 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: Saku | Statement: [Kazushi Sakuraba, nickname, Saku]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Saku
Context triple: [Kazushi Sakuraba, nickname, Saku]
  • A. Saku
    Saku is a Finnish given name most notably borne by former NHL and Montreal Canadiens captain Saku Koivu.
  • B. Saku
    Saku is a small town in northern Estonia known for its role as a local administrative center and for its historic brewery.
  • C. Sukeva
    Sukeva is a village in northern Finland best known for housing the Sukevan vankila prison facility.
  • D. Sakari
    Sakari is a Finnish given name commonly used for males, derived from the biblical name Zachary.
  • E. 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.
  • 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: Saku
Triple: [Kazushi Sakuraba, nickname, Saku]
Generated description
Saku is the nickname of Kazushi Sakuraba, a legendary Japanese mixed martial artist famed for his grappling skills and victories over multiple members of the Gracie family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Saku
Target entity description: Saku is the nickname of Kazushi Sakuraba, a legendary Japanese mixed martial artist famed for his grappling skills and victories over multiple members of the Gracie family.
  • A. Saku
    Saku is a Finnish given name most notably borne by former NHL and Montreal Canadiens captain Saku Koivu.
  • B. Saku
    Saku is a small town in northern Estonia known for its role as a local administrative center and for its historic brewery.
  • C. Sukeva
    Sukeva is a village in northern Finland best known for housing the Sukevan vankila prison facility.
  • D. Sakari
    Sakari is a Finnish given name commonly used for males, derived from the biblical name Zachary.
  • E. 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.
  • 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_69e245fc75348190a0288401044c8af8 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18f2bca4881909f6148d588948018 completed April 29, 2026, 4:55 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c30a4760881908b4e306b896df80e completed May 19, 2026, 9:43 a.m.
NEDg Description generation batch_6a0c32ab76988190917b76806a6c2c80 completed May 19, 2026, 9:51 a.m.
NED2 Entity disambiguation (via description) batch_6a0c3335e83c8190a9bee47e86215c05 completed May 19, 2026, 9:53 a.m.
Created at: April 17, 2026, 4:03 p.m.