Triple

T2875015
Position Surface form Disambiguated ID Type / Status
Subject Raka E56856 entity
Predicate character P662 FINISHED
Object Koki
Koki is a fictional character associated with Raka, likely appearing alongside them in a shared narrative or story.
 E305789 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: Koki | Statement: [Raka, character, Koki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Koki
Context triple: [Raka, character, Koki]
  • A. Kuki
    The Kuki are an indigenous ethnic group of Northeast India and surrounding regions, known for their distinct Tibeto-Burman language varieties, clan-based social structure, and rich cultural traditions.
  • B. Hacha-Kekan
    Hacha-Kekan is a traditional cultural festival of the Karbi people that showcases their indigenous rituals, music, dance, and communal celebrations.
  • C. Kibushi
    Kibushi is a Bantu language spoken primarily in Mayotte, where it serves as one of the island’s main regional languages.
  • D. Honancho
    Honancho is a neighborhood in Tokyo, Japan, known as a residential area with convenient access to central city districts via the Tokyo Metro Marunouchi Line.
  • E. Tigak
    Tigak is an Austronesian language of the Meso-Melanesian subgroup spoken primarily in parts of Papua New Guinea.
  • 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: Koki
Triple: [Raka, character, Koki]
Generated description
Koki is a fictional character associated with Raka, likely appearing alongside them in a shared narrative or story.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Koki
Target entity description: Koki is a fictional character associated with Raka, likely appearing alongside them in a shared narrative or story.
  • A. Kuki
    The Kuki are an indigenous ethnic group of Northeast India and surrounding regions, known for their distinct Tibeto-Burman language varieties, clan-based social structure, and rich cultural traditions.
  • B. Hacha-Kekan
    Hacha-Kekan is a traditional cultural festival of the Karbi people that showcases their indigenous rituals, music, dance, and communal celebrations.
  • C. Kibushi
    Kibushi is a Bantu language spoken primarily in Mayotte, where it serves as one of the island’s main regional languages.
  • D. Honancho
    Honancho is a neighborhood in Tokyo, Japan, known as a residential area with convenient access to central city districts via the Tokyo Metro Marunouchi Line.
  • E. Tigak
    Tigak is an Austronesian language of the Meso-Melanesian subgroup spoken primarily in parts of Papua New Guinea.
  • 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_69ab4a4ced288190ab6d3e062d10f7f6 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abe004a64481908f1897d9054a7368 completed March 7, 2026, 8:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01db780908190919d859205464b2e completed March 10, 2026, 1:33 p.m.
NEDg Description generation batch_69b0201470cc81909188573c3749dffb completed March 10, 2026, 1:43 p.m.
NED2 Entity disambiguation (via description) batch_69b020aa00888190a683a621f1e1a107 completed March 10, 2026, 1:46 p.m.
Created at: March 6, 2026, 10:03 p.m.