Triple

T6731264
Position Surface form Disambiguated ID Type / Status
Subject Drehu language E153638 entity
Predicate region P40 FINISHED
Object Lifou E651946 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: Lifou | Statement: [Drehu language, region, Lifou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lifou
Context triple: [Drehu language, region, Lifou]
  • A. Lifou Island chosen
    Lifou Island is a coral atoll in New Caledonia’s Loyalty Islands, known for its Melanesian Kanak culture, white-sand beaches, and use of the Drehu language.
  • B. Huahine
    Huahine is a lush, relatively untouched island in the Society Islands archipelago of French Polynesia, known for its tranquil lagoons, archaeological sites, and traditional Polynesian culture.
  • C. Raivavae
    Raivavae is a small, remote Polynesian island in French Polynesia known for its lush green peaks, surrounding lagoon, and traditional island culture.
  • D. Fatu Hiva
    Fatu Hiva is a remote, lushly forested volcanic island in French Polynesia’s Marquesas archipelago, known for its dramatic cliffs, deep valleys, and traditional Polynesian culture.
  • E. Futuna-Aniwa
    Futuna-Aniwa is a Polynesian language spoken primarily on the islands of Futuna and Aniwa in Vanuatu.
  • 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_69c6880bdd68819097de8b6099992682 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d16a30888190ae474d90bb71ac49 completed March 27, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7daf7529c8190b70ac11fb4c9ba32 completed March 28, 2026, 1:43 p.m.
Created at: March 27, 2026, 2:09 p.m.