Triple

T10077545
Position Surface form Disambiguated ID Type / Status
Subject New Hebrides E213806 entity
Predicate hasIsland P970 FINISHED
Object Malakula E153027 NE FINISHED

How this triple was built (2 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: [New Hebrides, hasIsland, Malakula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malakula
Context triple: [New Hebrides, hasIsland, Malakula]
  • A. Malakula chosen
    Malakula is one of the largest and most culturally diverse islands of Vanuatu, known for its many distinct languages and traditional customs.
  • B. Makilala
    Makilala is a municipality in the province of North Cotabato in the Philippines, known for its agricultural economy and proximity to Mount Apo.
  • C. Mukrang
    Mukrang is a principal deity revered in the Hemphu-Mukrang religious tradition of the Karbi people of Northeast India.
  • D. Mabila
    Mabila is the fortified Native American town in present-day Alabama that was the site of a major 1540 battle between Hernando de Soto’s Spanish expedition and the forces of Chief Tuskaloosa.
  • E. Kankia
    Kankia is a town and local government area in northern Nigeria, known for its role as an administrative and commercial center within Katsina State.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca839bf730819086900c323c9b8c95 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd02f47e08190bfeb641b202beecc completed April 2, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d29ad05bbc8190b103d66c9e786c86 completed April 5, 2026, 5:24 p.m.
Created at: March 30, 2026, 8:59 p.m.