Triple

T20691304
Position Surface form Disambiguated ID Type / Status
Subject Lau Islands E508556 entity
Predicate hasIsland P970 FINISHED
Object Kabara
Kabara is a small inhabited island in Fiji’s Lau archipelago, known for its traditional woodcarving and relatively undisturbed natural environment.
E1445374 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: Kabara | Statement: [Lau Islands, hasIsland, Kabara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kabara
Context triple: [Lau Islands, hasIsland, Kabara]
  • A. Ukbara
    Ukbara was a small medieval town in present-day Iraq, historically known as the birthplace or residence of several Islamic scholars such as Ibn Batta al-Ukbari.
  • B. Akabira
    Akabira is a small city in central Hokkaido, Japan, historically known as a coal-mining town.
  • C. Kahone
    Kahone is a historic town in Senegal that once served as the political center of the precolonial Serer kingdom of Saloum.
  • D. Yasa'ur
    Yasa'ur was a Mongol prince and military leader who played a significant role in the politics and conflicts of the Chagatai Khanate during the early 14th century.
  • E. Kutama
    Kutama is a rural village in the Zvimba District of northern Zimbabwe, known primarily as the birthplace of former president Robert Mugabe.
  • 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: Kabara
Triple: [Lau Islands, hasIsland, Kabara]
Generated description
Kabara is a small inhabited island in Fiji’s Lau archipelago, known for its traditional woodcarving and relatively undisturbed natural environment.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kabara
Target entity description: Kabara is a small inhabited island in Fiji’s Lau archipelago, known for its traditional woodcarving and relatively undisturbed natural environment.
  • A. Ukbara
    Ukbara was a small medieval town in present-day Iraq, historically known as the birthplace or residence of several Islamic scholars such as Ibn Batta al-Ukbari.
  • B. Akabira
    Akabira is a small city in central Hokkaido, Japan, historically known as a coal-mining town.
  • C. Kahone
    Kahone is a historic town in Senegal that once served as the political center of the precolonial Serer kingdom of Saloum.
  • D. Yasa'ur
    Yasa'ur was a Mongol prince and military leader who played a significant role in the politics and conflicts of the Chagatai Khanate during the early 14th century.
  • E. Kutama
    Kutama is a rural village in the Zvimba District of northern Zimbabwe, known primarily as the birthplace of former president Robert Mugabe.
  • 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_69e0b4c1ed408190b72dd26b1e33f8a1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c10d83548190a52b9ef84c8f9205 completed April 21, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08d7e43a3c81909f63e63e30e9c435 completed May 16, 2026, 8:47 p.m.
NEDg Description generation batch_6a08d91216bc8190909e0e37f6d5e612 completed May 16, 2026, 8:52 p.m.
NED2 Entity disambiguation (via description) batch_6a08d99214b48190b0ffba4026d3fa39 completed May 16, 2026, 8:54 p.m.
Created at: April 16, 2026, 12:08 p.m.