Triple

T18005503
Position Surface form Disambiguated ID Type / Status
Subject Iki Airport E430734 entity
Predicate hasCityServed P3936 FINISHED
Object Iki
Iki is a Japanese island city in Nagasaki Prefecture known for its coastal scenery, historical sites, and connection to nearby Kyushu and Korea.
 E1301456 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: Iki | Statement: [Iki Airport, hasCityServed, Iki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Iki
Context triple: [Iki Airport, hasCityServed, Iki]
  • A. Iki
    Iki is one of the signature illumination themes of Tokyo Skytree, featuring an elegant, cool-toned lighting design inspired by traditional Edo aesthetics.
  • B. Iken
    Iken is a village in Suffolk, England, known for its ancient church and association with the Anglo-Saxon saint Botwulf (St Botolph).
  • C. Ikena
    "Ikena" is a Hawaiian-themed music album by actress and singer Tia Carrere, showcasing her vocal performances in the Hawaiian language and traditional island styles.
  • D. Ihi
    Ihi is an ancient Egyptian child god linked to music and joy, often depicted playing the sistrum and associated with the goddess Hathor.
  • E. ICHI
    ICHI is a standardized global classification system developed by the World Health Organization to systematically code and describe health interventions across different countries and healthcare settings.
  • 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: Iki
Triple: [Iki Airport, hasCityServed, Iki]
Generated description
Iki is a Japanese island city in Nagasaki Prefecture known for its coastal scenery, historical sites, and connection to nearby Kyushu and Korea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Iki
Target entity description: Iki is a Japanese island city in Nagasaki Prefecture known for its coastal scenery, historical sites, and connection to nearby Kyushu and Korea.
  • A. Iki
    Iki is one of the signature illumination themes of Tokyo Skytree, featuring an elegant, cool-toned lighting design inspired by traditional Edo aesthetics.
  • B. Iken
    Iken is a village in Suffolk, England, known for its ancient church and association with the Anglo-Saxon saint Botwulf (St Botolph).
  • C. Ikena
    "Ikena" is a Hawaiian-themed music album by actress and singer Tia Carrere, showcasing her vocal performances in the Hawaiian language and traditional island styles.
  • D. Ihi
    Ihi is an ancient Egyptian child god linked to music and joy, often depicted playing the sistrum and associated with the goddess Hathor.
  • E. ICHI
    ICHI is a standardized global classification system developed by the World Health Organization to systematically code and describe health interventions across different countries and healthcare settings.
  • 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b51ba1888190a339d726e92f376b completed April 19, 2026, 10:57 a.m.
NED1 Entity disambiguation (via context triple) batch_6a03431b4b6c8190836e7856a93d485c completed May 12, 2026, 3:11 p.m.
NEDg Description generation batch_6a03447c0530819082d554592eec03ca completed May 12, 2026, 3:17 p.m.
NED2 Entity disambiguation (via description) batch_6a034552e424819087b23bcf3f688523 completed May 12, 2026, 3:20 p.m.
Created at: April 10, 2026, 10:24 a.m.