Triple

T5377930
Position Surface form Disambiguated ID Type / Status
Subject Fukuoka Prefecture E113007 entity
Predicate hasCity P316 FINISHED
Object Kama
Kama is a small city located in Japan’s Fukuoka Prefecture on the island of Kyushu.
 E515179 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: Kama | Statement: [Fukuoka Prefecture, hasCity, Kama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kama
Context triple: [Fukuoka Prefecture, hasCity, Kama]
  • A. Kaa
    Kaa is a giant, hypnotic python who serves as a dangerous and manipulative predator in Disney’s live-action adaptation of The Jungle Book.
  • B. Tantamani
    Tantamani was a Kushite king of the 25th Dynasty of Egypt, known for his brief attempt to restore Nubian control over Egypt before being driven back by the Assyrians.
  • C. Maasim
    Maasim is a coastal municipality in the province of South Cotabato on the island of Mindanao in the Philippines, known for agriculture and fishing.
  • D. Kile
    Kile is a KDE-based integrated LaTeX editor that provides tools for writing, compiling, and previewing LaTeX documents efficiently.
  • E. Maroelap
    Maroelap is the former name of Maloelap Atoll, a coral atoll in the Ratak Chain of the Marshall Islands in the central Pacific Ocean.
  • 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: Kama
Triple: [Fukuoka Prefecture, hasCity, Kama]
Generated description
Kama is a small city located in Japan’s Fukuoka Prefecture on the island of Kyushu.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kama
Target entity description: Kama is a small city located in Japan’s Fukuoka Prefecture on the island of Kyushu.
  • A. Kaa
    Kaa is a giant, hypnotic python who serves as a dangerous and manipulative predator in Disney’s live-action adaptation of The Jungle Book.
  • B. Tantamani
    Tantamani was a Kushite king of the 25th Dynasty of Egypt, known for his brief attempt to restore Nubian control over Egypt before being driven back by the Assyrians.
  • C. Maasim
    Maasim is a coastal municipality in the province of South Cotabato on the island of Mindanao in the Philippines, known for agriculture and fishing.
  • D. Kile
    Kile is a KDE-based integrated LaTeX editor that provides tools for writing, compiling, and previewing LaTeX documents efficiently.
  • E. Maroelap
    Maroelap is the former name of Maloelap Atoll, a coral atoll in the Ratak Chain of the Marshall Islands in the central Pacific Ocean.
  • 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_69bd4436a1988190af18dcff7fd306b4 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd86cb13ac81909dc364e7d3605844 completed March 20, 2026, 5:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf29465ff0819082c05dbe40a306f3 completed March 21, 2026, 11:27 p.m.
NEDg Description generation batch_69bf29e0c9708190ac76c8306b76f0fa completed March 21, 2026, 11:29 p.m.
NED2 Entity disambiguation (via description) batch_69bf2a93efa88190b641924bb652068c completed March 21, 2026, 11:32 p.m.
Created at: March 20, 2026, 2:03 p.m.