Triple

T2707663
Position Surface form Disambiguated ID Type / Status
Subject Tongans E59380 entity
Predicate populationConcentration P23004 FINISHED
Object Haʻapai E186472 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: Haʻapai | Statement: [Tongans, populationConcentration, Haʻapai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haʻapai
Context triple: [Tongans, populationConcentration, Haʻapai]
  • A. Haʻapai chosen
    Haʻapai is a central group of low-lying coral islands and reefs in the Kingdom of Tonga, known for its remote beaches, traditional villages, and rich marine life.
  • B. Hiri Motu
    Hiri Motu is an Austronesian lingua franca and one of the official languages of Papua New Guinea, historically used for trade and communication among diverse ethnic groups.
  • C. Savaiʻi
    Savaiʻi is the largest and one of the main islands of Samoa, known for its volcanic landscapes, traditional villages, and relatively undeveloped, rural character.
  • D. Rarotongan
    Rarotongan is a Polynesian language spoken primarily in the Cook Islands, where it serves as one of the main indigenous languages.
  • E. Taveuni
    Taveuni is Fiji’s third-largest island, famed for its lush rainforests, rich biodiversity, and world-class diving sites along the Somosomo Strait.
  • 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_69ab4ac66bc88190b9e4afa5fc843f72 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abda73de1c81908f5d6b0383e23144 completed March 7, 2026, 7:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc030c9b88190934f96a8ff74c4a7 completed March 10, 2026, 6:54 a.m.
Created at: March 6, 2026, 9:55 p.m.