Triple

T14790689
Position Surface form Disambiguated ID Type / Status
Subject Sitiveni Rabuka E347645 entity
Predicate name P16 FINISHED
Object Sitiveni Rabuka E347645 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: Sitiveni Rabuka | Statement: [Sitiveni Rabuka, name, Sitiveni Rabuka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sitiveni Rabuka
Context triple: [Sitiveni Rabuka, name, Sitiveni Rabuka]
  • A. Sitiveni Rabuka chosen
    Sitiveni Rabuka is a Fijian political and military leader best known for leading the 1987 coups and later serving as the country’s prime minister.
  • B. Tito Melema
    Tito Melema is a charming yet morally weak young Greek scholar whose opportunism and betrayal drive much of the psychological and ethical drama in George Eliot’s novel "Romola."
  • C. Feleti Sevele
    Feleti Sevele is a Tongan politician and economist who served as the country's first commoner Prime Minister in the modern era.
  • D. Siaosi Sovaleni
    Siaosi Sovaleni is a Tongan politician who has served as the country's prime minister, leading its government and national policy.
  • E. Amason Kingi
    Amason Kingi is a Kenyan politician and lawyer who has served in various senior government roles, including as a county governor, before becoming Speaker of the Senate.
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decd5d134c819080ee788b2e34163a completed April 14, 2026, 11:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe24bc8464819096b019f1e927d1a9 completed May 8, 2026, 6 p.m.
Created at: April 10, 2026, 1:31 a.m.