Triple

T22594949
Position Surface form Disambiguated ID Type / Status
Subject Solor E574649 entity
Predicate locatedBetween P1262 FINISHED
Object Adonara NE NERFINISHED

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: Adonara | Statement: [Solor, locatedBetween, Adonara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adonara
Context triple: [Solor, locatedBetween, Adonara]
  • A. Adonara Island chosen
    Adonara Island is a small volcanic island in eastern Indonesia’s Lesser Sunda Islands, known for its traditional communities and location between Flores and Lembata.
  • B. Mahorais
    Mahorais is a French-based creole language spoken primarily on the island of Mayotte in the Indian Ocean.
  • C. Kuata Island
    Kuata Island is a small tropical island in Fiji’s Yasawa archipelago, known for its rugged volcanic landscapes, clear waters, and popular snorkeling and diving spots.
  • D. Giraavaru
    Giraavaru is a small inhabited island in the Maldives, known for its traditional Maldivian community and surrounding coral reef environment.
  • E. Hatoma Island
    Hatoma Island is a small, remote island in Japan’s Yaeyama archipelago, known for its traditional Ryukyuan culture, coral reefs, and tranquil, sparsely populated environment.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245bc11308190b69d794d5d1e0bb6 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f16164d690819096f7c4efb6cedad9 completed April 29, 2026, 1:39 a.m.
Created at: April 17, 2026, 2:49 p.m.