Triple

T1311352
Position Surface form Disambiguated ID Type / Status
Subject Vanuatu E27996 entity
Predicate hasIsland P970 FINISHED
Object Malakula
Malakula is one of the largest and most culturally diverse islands of Vanuatu, known for its many distinct languages and traditional customs.
E153027 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: Malakula | Statement: [Vanuatu, hasIsland, Malakula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malakula
Context triple: [Vanuatu, hasIsland, Malakula]
  • A. Khoni
    Khoni is a small town in western Georgia’s Imereti region, known for its historical churches and surrounding natural landscapes.
  • B. Negaraku
    Negaraku is the national anthem of Malaysia, symbolizing the country's sovereignty and unity.
  • C. Malaita
    Malaita is one of the main islands of the Solomon Islands in the South Pacific, known for its large population, rich traditional culture, and historical role in regional labor trade.
  • D. Shabara
    Shabara was an early Indian philosopher and commentator best known for his influential exegesis on the Purva Mimamsa school of Hindu philosophy.
  • E. Watugaluh
    Watugaluh was an important historical city in Java that served as the political and administrative center of the Medang Kingdom.
  • 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: Malakula
Triple: [Vanuatu, hasIsland, Malakula]
Generated description
Malakula is one of the largest and most culturally diverse islands of Vanuatu, known for its many distinct languages and traditional customs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Malakula
Target entity description: Malakula is one of the largest and most culturally diverse islands of Vanuatu, known for its many distinct languages and traditional customs.
  • A. Khoni
    Khoni is a small town in western Georgia’s Imereti region, known for its historical churches and surrounding natural landscapes.
  • B. Negaraku
    Negaraku is the national anthem of Malaysia, symbolizing the country's sovereignty and unity.
  • C. Malaita
    Malaita is one of the main islands of the Solomon Islands in the South Pacific, known for its large population, rich traditional culture, and historical role in regional labor trade.
  • D. Shabara
    Shabara was an early Indian philosopher and commentator best known for his influential exegesis on the Purva Mimamsa school of Hindu philosophy.
  • E. Watugaluh
    Watugaluh was an important historical city in Java that served as the political and administrative center of the Medang Kingdom.
  • 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_69a496d7d83481908f83085854e51328 completed March 1, 2026, 7:43 p.m.
NER Named-entity recognition batch_69a4c1560f888190bdd9107b08395e0b completed March 1, 2026, 10:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69acc6255b808190823bc240365ed304 completed March 8, 2026, 12:43 a.m.
NEDg Description generation batch_69acc684fb34819097fbb1659032d3c2 completed March 8, 2026, 12:44 a.m.
NED2 Entity disambiguation (via description) batch_69acc6ec853c8190b60bd2d876605c48 completed March 8, 2026, 12:46 a.m.
Created at: March 1, 2026, 7:51 p.m.