Triple

T20063538
Position Surface form Disambiguated ID Type / Status
Subject Kobe, Hyogo, Japan E499546 entity
Predicate hasWard P14475 FINISHED
Object Suma-ku
Suma-ku is a coastal ward of Kobe in Hyogo Prefecture, Japan, known for its beaches, historic sites, and residential neighborhoods.
 E1408350 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: Suma-ku | Statement: [Kobe, Hyogo, Japan, hasWard, Suma-ku]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Suma-ku
Context triple: [Kobe, Hyogo, Japan, hasWard, Suma-ku]
  • A. Sakumono
    Sakumono is a coastal suburban community in the Greater Accra Region of Ghana, known for its residential estates and proximity to the Sakumono Lagoon and beach.
  • B. Senzoku
    Senzoku is a neighborhood in Tokyo, Japan, known as a residential area with local shops and convenient access to central parts of the city.
  • C. Ogakumonjo
    Ogakumonjo is a historic structure within Kyoto Imperial Palace, traditionally associated with imperial academic or archival functions in Japan’s former capital.
  • D. Kosubosu
    Kosubosu is a town in Nigeria that serves as the administrative center of Baruten Local Government Area in Kwara State.
  • E. Munefusa
    Munefusa is the birth name of Matsuo Bashō, the renowned 17th-century Japanese haiku poet and travel writer.
  • 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: Suma-ku
Triple: [Kobe, Hyogo, Japan, hasWard, Suma-ku]
Generated description
Suma-ku is a coastal ward of Kobe in Hyogo Prefecture, Japan, known for its beaches, historic sites, and residential neighborhoods.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Suma-ku
Target entity description: Suma-ku is a coastal ward of Kobe in Hyogo Prefecture, Japan, known for its beaches, historic sites, and residential neighborhoods.
  • A. Sakumono
    Sakumono is a coastal suburban community in the Greater Accra Region of Ghana, known for its residential estates and proximity to the Sakumono Lagoon and beach.
  • B. Senzoku
    Senzoku is a neighborhood in Tokyo, Japan, known as a residential area with local shops and convenient access to central parts of the city.
  • C. Ogakumonjo
    Ogakumonjo is a historic structure within Kyoto Imperial Palace, traditionally associated with imperial academic or archival functions in Japan’s former capital.
  • D. Kosubosu
    Kosubosu is a town in Nigeria that serves as the administrative center of Baruten Local Government Area in Kwara State.
  • E. Munefusa
    Munefusa is the birth name of Matsuo Bashō, the renowned 17th-century Japanese haiku poet and travel writer.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66377b6b48190a0a37279f285123e completed April 20, 2026, 5:33 p.m.
NED1 Entity disambiguation (via context triple) batch_6a081612662c81909cb1e90910ca76ac completed May 16, 2026, 7 a.m.
NEDg Description generation batch_6a0816d4a8e081909930e2e379a56071 completed May 16, 2026, 7:03 a.m.
NED2 Entity disambiguation (via description) batch_6a081742ed8481908a424a3d05368e46 completed May 16, 2026, 7:05 a.m.
Created at: April 11, 2026, 3:39 p.m.