Triple

T17025996
Position Surface form Disambiguated ID Type / Status
Subject Winners and Sinners E413064 entity
Predicate starring P1507 FINISHED
Object John Shum E1246442 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: John Shum | Statement: [Winners and Sinners, starring, John Shum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Shum
Context triple: [Winners and Sinners, starring, John Shum]
  • A. John Shum chosen
    John Shum is a Hong Kong actor and comedian known for his roles in 1980s action and comedy films.
  • B. John Shinn
    John Shinn was the founder of the Academy of Natural Sciences of Drexel University, one of the oldest natural history institutions in the United States.
  • C. Christopher Murney
    Christopher Murney is an American character actor and voice actor known for his work in film, television, and animation, including a prominent role on the series "Remember WENN."
  • D. Michael Colleary
    Michael Colleary is an American screenwriter and producer best known for co-writing the action film "Face/Off" and working on various Hollywood genre movies and television projects.
  • E. John Tormey
    John Tormey is an American character actor best known for his supporting role in Jim Jarmusch’s crime film "Ghost Dog: The Way of the Samurai."
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d5d46a5081908bc5681621dd8534 completed April 18, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012334c3b48190b125ab926450c45b completed May 11, 2026, 12:30 a.m.
Created at: April 10, 2026, 5:33 a.m.