Triple

T22209609
Position Surface form Disambiguated ID Type / Status
Subject Ann Hui E548905 entity
Predicate notableWork P4 FINISHED
Object Boat People 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: Boat People | Statement: [Ann Hui, notableWork, Boat People]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Boat People
Context triple: [Ann Hui, notableWork, Boat People]
  • A. Boat People chosen
    Boat People is a 1982 Hong Kong drama film directed by Ann Hui that portrays the harsh realities faced by Vietnamese refugees after the Vietnam War.
  • B. We Are Boats
    We Are Boats is a 2018 fantasy drama film following interconnected lives and the spiritual journeys that link them.
  • C. A Bigger Boat
    A Bigger Boat is a film and television production company known for developing genre-driven and independent projects.
  • D. When the Boat Comes In
    When the Boat Comes In is a British television drama series set in the interwar period in North East England, following the struggles of working-class communities.
  • E. River People
    River People is the English name for the Akimel O’otham, a Native American people traditionally living along the Gila and Salt Rivers in what is now Arizona.
  • 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_69e11e3f7e04819089806d81d5ac431e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12b2aefb881909bddbabd4be0bd58 completed April 28, 2026, 9:48 p.m.
Created at: April 16, 2026, 8:36 p.m.