Triple

T8558599
Position Surface form Disambiguated ID Type / Status
Subject Sun Pictures E202635 entity
Predicate partOf P40 FINISHED
Object Sun Group E615153 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: Sun Group | Statement: [Sun Pictures, partOf, Sun Group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sun Group
Context triple: [Sun Pictures, partOf, Sun Group]
  • A. Sun Group chosen
    Sun Group is a major Vietnamese real estate and tourism developer known for creating large-scale entertainment, resort, and infrastructure projects across the country.
  • B. Travelers Group
    Travelers Group was a major American financial services conglomerate that became best known for its landmark 1998 merger with Citicorp to form Citigroup.
  • C. Genting Group
    Genting Group is a Malaysian multinational conglomerate best known for its global portfolio of integrated resorts, casinos, and leisure and hospitality businesses.
  • D. Hồng Hà
    Hồng Hà is the Vietnamese name for the Red River, a major river in Southeast Asia that flows from China through northern Vietnam into the Gulf of Tonkin.
  • E. Mandelay Entertainment Group
    Mandalay Entertainment Group is an American film and television production company founded by producer Peter Guber, known for developing and financing a wide range of Hollywood movies and series.
  • 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_69ca8326e6c881908ff720d6abaebdc5 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe9485dd88190bc2cf2adf39d48ee completed March 31, 2026, 3:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce894d82588190b558d5b2dc65eafe completed April 2, 2026, 3:20 p.m.
Created at: March 30, 2026, 6:20 p.m.