Triple

T15964908
Position Surface form Disambiguated ID Type / Status
Subject Janet Yang E387161 entity
Predicate produced P490 FINISHED
Object Empire of the Sun E264224 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: Empire of the Sun | Statement: [Janet Yang, produced, Empire of the Sun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Empire of the Sun
Context triple: [Janet Yang, produced, Empire of the Sun]
  • A. Empire of the Sun chosen
    Empire of the Sun is a 1987 coming-of-age war film directed by Steven Spielberg that follows a young British boy’s struggle for survival in a Japanese internment camp during World War II.
  • B. The Age
    The Age is a major Australian daily newspaper based in Melbourne, known for its comprehensive news coverage and influential journalism.
  • C. Hugo
    Hugo is a masculine given name of Germanic origin, commonly used in various European and Spanish-speaking countries.
  • D. Hugo
    Hugo is a 2011 fantasy adventure film directed by Martin Scorsese, acclaimed for its innovative use of 3D and its homage to early cinema and filmmaker Georges Méliès.
  • E. Hugo
    Hugo is a tragic young character from the manga series "Gunnm" (also known as "Battle Angel Alita"), whose dreams of reaching the floating city Zalem drive much of the early emotional narrative.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1572475948190af0e3b12de0f6cea completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3c5a7d48190891e69314e67e9af completed May 9, 2026, 11:31 p.m.
Created at: April 10, 2026, 4:54 a.m.