Triple

T18028956
Position Surface form Disambiguated ID Type / Status
Subject Kiki Sukezane E431335 entity
Predicate givenName P17 FINISHED
Object Kiki
Kiki is a Japanese actress best known internationally for her role as Miko Otomo in the television series "Heroes Reborn."
 E1302018 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: Kiki | Statement: [Kiki Sukezane, givenName, Kiki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kiki
Context triple: [Kiki Sukezane, givenName, Kiki]
  • A. Kiki
    Kiki is one of the central overworked and underappreciated mothers in the comedy film "Bad Moms," known for her shy, anxious personality and eventual rebellious transformation.
  • B. Kiki
    Kiki was the nickname of Hazen "Kiki" Cuyler, a Hall of Fame Major League Baseball outfielder known for his speed and hitting in the 1920s and 1930s.
  • C. Let’s Have a Kiki
    "Let’s Have a Kiki" is a campy, spoken-word-driven dance-pop song by Scissor Sisters that became a queer club anthem and viral cult favorite.
  • D. Natafuta Kiki
    Natafuta Kiki is a popular Tanzanian Bongo Flava song by Rayvanny known for its catchy melody and playful lyrics about seeking attention.
  • E. Kiki Aru
    Kiki Aru is a young Munchkin boy and powerful but misguided magician who serves as the central antagonist in L. Frank Baum’s Oz novel "The Magic of Oz."
  • 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: Kiki
Triple: [Kiki Sukezane, givenName, Kiki]
Generated description
Kiki is a Japanese actress best known internationally for her role as Miko Otomo in the television series "Heroes Reborn."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kiki
Target entity description: Kiki is a Japanese actress best known internationally for her role as Miko Otomo in the television series "Heroes Reborn."
  • A. Kiki
    Kiki is one of the central overworked and underappreciated mothers in the comedy film "Bad Moms," known for her shy, anxious personality and eventual rebellious transformation.
  • B. Kiki
    Kiki was the nickname of Hazen "Kiki" Cuyler, a Hall of Fame Major League Baseball outfielder known for his speed and hitting in the 1920s and 1930s.
  • C. Let’s Have a Kiki
    "Let’s Have a Kiki" is a campy, spoken-word-driven dance-pop song by Scissor Sisters that became a queer club anthem and viral cult favorite.
  • D. Natafuta Kiki
    Natafuta Kiki is a popular Tanzanian Bongo Flava song by Rayvanny known for its catchy melody and playful lyrics about seeking attention.
  • E. Kiki Aru
    Kiki Aru is a young Munchkin boy and powerful but misguided magician who serves as the central antagonist in L. Frank Baum’s Oz novel "The Magic of Oz."
  • 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_69d8b9050fb48190890155145deb0a66 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4be332a7081909124abdd98430a8a completed April 19, 2026, 11:36 a.m.
NED1 Entity disambiguation (via context triple) batch_6a03432cd3088190892e4c23e9e42b4e completed May 12, 2026, 3:11 p.m.
NEDg Description generation batch_6a034673924c81908ce78f3040b0b6e7 completed May 12, 2026, 3:25 p.m.
NED2 Entity disambiguation (via description) batch_6a0346e675e0819098af9e720adda576 completed May 12, 2026, 3:27 p.m.
Created at: April 10, 2026, 10:25 a.m.