Triple

T10349346
Position Surface form Disambiguated ID Type / Status
Subject Tokelauan E243838 entity
Predicate nativeTo P410 FINISHED
Object Atafu E291718 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: Atafu | Statement: [Tokelauan, nativeTo, Atafu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Atafu
Context triple: [Tokelauan, nativeTo, Atafu]
  • A. Atafu chosen
    Atafu is one of the three main atolls of Tokelau in the South Pacific Ocean, serving as a key population and administrative center for the territory.
  • B. Tahuata
    Tahuata is a small, rugged island in the southern Marquesas archipelago of French Polynesia, known for its traditional Polynesian culture and remote, scenic landscapes.
  • C. Ofu
    Ofu is a small volcanic island in the Manuʻa group of American Samoa, known for its pristine beaches, coral reefs, and inclusion in the National Park of American Samoa.
  • D. Ofu
    Ofu is a small island in the Vavaʻu island group of the Kingdom of Tonga, known for its tranquil beaches and traditional Polynesian village life.
  • E. Pa'a
    Pa'a is a Chadic language spoken in northern Nigeria, closely related to and geographically near the Warji language.
  • 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_69d381b22b8c8190aaed476be5f872a9 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e946cbb881909b88536d0107995d completed April 7, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7951e65948190a25e559ba94be3c7 completed April 9, 2026, 12:01 p.m.
Created at: April 6, 2026, 11:57 a.m.