Triple

T20072426
Position Surface form Disambiguated ID Type / Status
Subject Fuliru E499770 entity
Predicate alternativeName P39 FINISHED
Object Fuliiru 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: Fuliiru | Statement: [Fuliru, alternativeName, Fuliiru]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fuliiru
Context triple: [Fuliru, alternativeName, Fuliiru]
  • A. Fuliiro chosen
    The Fuliiro are an ethnic group living in close proximity to the Shi people in Central Africa, sharing regional cultural and historical ties.
  • B. Filiti
    Filiti is an Italian surname most notably associated with Tony Filiti, a relative of Sylvester Stallone.
  • C. Faleniu
    Faleniu is a village on the island of Tutuila in American Samoa, located inland not far from Pago Pago and its international airport.
  • D. Felletin
    Felletin is a historic French town in the Creuse department renowned as a traditional center of tapestry weaving closely linked to the famed Aubusson tapestry industry.
  • E. Faltine
    Faltine are powerful extra-dimensional energy beings in the Marvel Universe, known for their immense mystical abilities and for producing entities like Dormammu.
  • 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e664392c748190a6cc472f80b8c74b completed April 20, 2026, 5:36 p.m.
Created at: April 11, 2026, 3:40 p.m.