Triple

T19675771
Position Surface form Disambiguated ID Type / Status
Subject Ungyō E472447 entity
Predicate depicts P1581 FINISHED
Object closed-mouthed Nio
Closed-mouthed Nio, or Ungyō, is one of the two guardian deities in Japanese Buddhist temple gates, symbolizing latent strength and protection through his silent, closed-mouth expression.
 E1390486 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: closed-mouthed Nio | Statement: [Ungyō, depicts, closed-mouthed Nio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: closed-mouthed Nio
Context triple: [Ungyō, depicts, closed-mouthed Nio]
  • A. Nio
    Nio is a Chinese electric vehicle manufacturer known for its premium smart EVs and battery-swapping technology.
  • B. NOK
    NOK is the ICAO airline designator assigned to the Thai low-cost carrier Nok Air.
  • C. NOK
    NOK is the official currency code for the Norwegian krone, the national currency of Norway.
  • D. NVO
    NVO is the stock ticker symbol for Novo Nordisk, a global pharmaceutical company best known for its diabetes care products.
  • E. NIKL
    NIKL is the abbreviated name of South Korea’s National Institute of Korean Language, the government body responsible for researching, standardizing, and promoting the Korean language.
  • 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: closed-mouthed Nio
Triple: [Ungyō, depicts, closed-mouthed Nio]
Generated description
Closed-mouthed Nio, or Ungyō, is one of the two guardian deities in Japanese Buddhist temple gates, symbolizing latent strength and protection through his silent, closed-mouth expression.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: closed-mouthed Nio
Target entity description: Closed-mouthed Nio, or Ungyō, is one of the two guardian deities in Japanese Buddhist temple gates, symbolizing latent strength and protection through his silent, closed-mouth expression.
  • A. Nio
    Nio is a Chinese electric vehicle manufacturer known for its premium smart EVs and battery-swapping technology.
  • B. NOK
    NOK is the ICAO airline designator assigned to the Thai low-cost carrier Nok Air.
  • C. NOK
    NOK is the official currency code for the Norwegian krone, the national currency of Norway.
  • D. NVO
    NVO is the stock ticker symbol for Novo Nordisk, a global pharmaceutical company best known for its diabetes care products.
  • E. NIKL
    NIKL is the abbreviated name of South Korea’s National Institute of Korean Language, the government body responsible for researching, standardizing, and promoting the Korean language.
  • 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_69d8e514f2e08190ba70a4449519d218 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e641bbea8c8190b0ad841d95068e0e completed April 20, 2026, 3:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0787c261808190b4bf53d0a7ecd54b completed May 15, 2026, 8:53 p.m.
NEDg Description generation batch_6a0789df479881909750ae3fcf509dd9 completed May 15, 2026, 9:02 p.m.
NED2 Entity disambiguation (via description) batch_6a078a70157081908b7137984dc05e42 completed May 15, 2026, 9:04 p.m.
Created at: April 10, 2026, 1:45 p.m.