Triple

T14572325
Position Surface form Disambiguated ID Type / Status
Subject Bellona Island E341947 entity
Predicate hasAlternativeName P39 FINISHED
Object Mungiki
Mungiki is an alternative name for Bellona Island, a small inhabited island in the Solomon Islands known for its raised coral limestone formation and Polynesian culture.
E1106447 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: Mungiki | Statement: [Bellona Island, hasAlternativeName, Mungiki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mungiki
Context triple: [Bellona Island, hasAlternativeName, Mungiki]
  • A. Muno
    Muno is a village in the municipality of Florenville in the Wallonia region of southern Belgium.
  • B. Ogakumonjo
    Ogakumonjo is a historic structure within Kyoto Imperial Palace, traditionally associated with imperial academic or archival functions in Japan’s former capital.
  • C. Muchita
    Muchita is a surname, notably borne by individuals such as the artist known as Havoc.
  • D. Mungguy
    Mungguy are the Aboriginal traditional owners and custodians of the land that includes Kakadu National Park in Australia’s Northern Territory.
  • E. Pipikoro
    Pipikoro is an Austronesian language spoken in Central Sulawesi, Indonesia, known locally as an alternate name for the Uma 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: Mungiki
Triple: [Bellona Island, hasAlternativeName, Mungiki]
Generated description
Mungiki is an alternative name for Bellona Island, a small inhabited island in the Solomon Islands known for its raised coral limestone formation and Polynesian culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mungiki
Target entity description: Mungiki is an alternative name for Bellona Island, a small inhabited island in the Solomon Islands known for its raised coral limestone formation and Polynesian culture.
  • A. Muno
    Muno is a village in the municipality of Florenville in the Wallonia region of southern Belgium.
  • B. Ogakumonjo
    Ogakumonjo is a historic structure within Kyoto Imperial Palace, traditionally associated with imperial academic or archival functions in Japan’s former capital.
  • C. Muchita
    Muchita is a surname, notably borne by individuals such as the artist known as Havoc.
  • D. Mungguy
    Mungguy are the Aboriginal traditional owners and custodians of the land that includes Kakadu National Park in Australia’s Northern Territory.
  • E. Pipikoro
    Pipikoro is an Austronesian language spoken in Central Sulawesi, Indonesia, known locally as an alternate name for the Uma 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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb3f33b1c8190bb447788bfd28d51 completed April 14, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8aca591081908db149ec517a999b completed May 8, 2026, 7:03 a.m.
NEDg Description generation batch_69fd8bd70488819083f40c38575f3071 completed May 8, 2026, 7:08 a.m.
NED2 Entity disambiguation (via description) batch_69fd8d4f2e848190a3c4c423c0ffed50 completed May 8, 2026, 7:14 a.m.
Created at: April 10, 2026, 1:24 a.m.