Triple

T12944813
Position Surface form Disambiguated ID Type / Status
Subject Yojo E309732 entity
Predicate countryOfOriginInFiction P26 FINISHED
Object Rokovoko E309734 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: Rokovoko | Statement: [Yojo, countryOfOriginInFiction, Rokovoko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rokovoko
Context triple: [Yojo, countryOfOriginInFiction, Rokovoko]
  • A. Rokovoko chosen
    Rokovoko is the fictional, remote South Pacific island homeland of Queequeg in Herman Melville’s novel "Moby-Dick."
  • B. Rauco
    Rauco is a rural municipality and commune in central Chile’s Maule Region, known for its agricultural activities and proximity to the city of Curicó.
  • C. Bompoka
    Bompoka is a small, remote island that forms part of India’s Nicobar Islands archipelago in the eastern Indian Ocean.
  • D. Wokolo
    Wokolo is the largest known impact crater on Umbriel, one of Uranus’s major moons.
  • E. Tagakaolo
    Tagakaolo is an indigenous ethnolinguistic group in the southern Philippines, primarily in parts of Davao and Sarangani, known for its distinct Austronesian language and cultural traditions.
  • 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_69d7bdfb57a88190836b743e2825feca completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97e1b3694819098527dcea3cfed93 completed April 10, 2026, 10:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6af73e6348190be114e8c5ad181bf completed May 3, 2026, 2:14 a.m.
Created at: April 9, 2026, 5:43 p.m.