Triple

T3351745
Position Surface form Disambiguated ID Type / Status
Subject Gilbert Islands E70511 entity
Predicate hasIsland P970 FINISHED
Object Maiana E113683 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: Maiana | Statement: [Gilbert Islands, hasIsland, Maiana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maiana
Context triple: [Gilbert Islands, hasIsland, Maiana]
  • A. Maiana chosen
    Maiana is a low-lying coral atoll in the central Pacific nation of Kiribati, known for its traditional village life and vulnerability to sea-level rise.
  • B. Kuanua
    Kuanua is an Austronesian language spoken primarily by the Tolai people of East New Britain in Papua New Guinea.
  • C. Tagbanwa
    Tagbanwa is an indigenous Philippine script historically used by the Tagbanwa people of Palawan for writing their Austronesian language.
  • D. Thaya
    Thaya is a river in Central Europe that flows through Austria and the Czech Republic, forming part of the border between the two countries.
  • E. Ranna
    Ranna was a prominent 10th-century Kannada poet, celebrated as one of the “three gems” of early Kannada literature for his influential epic and courtly works.
  • 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_69ad85a4ef7c8190a29e2bbd6fa454e4 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb221a7d8819086cd0f826eca0fe8 completed March 8, 2026, 5:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3252f3f248190bb61db5c4fd2781a completed March 12, 2026, 8:42 p.m.
Created at: March 8, 2026, 3:12 p.m.