Triple

T22448136
Position Surface form Disambiguated ID Type / Status
Subject Gunpowder E554916 entity
Predicate starring P1507 FINISHED
Object Tom Cullen 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: Tom Cullen | Statement: [Gunpowder, starring, Tom Cullen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Cullen
Context triple: [Gunpowder, starring, Tom Cullen]
  • A. Tom Cullen
    Tom Cullen is a co-founder of Sonos, the company known for pioneering wireless multi-room home audio systems.
  • B. Tom Cullen
    Tom Cullen is a gentle, intellectually disabled yet perceptive survivor from Stephen King’s post-apocalyptic novel "The Stand," known for his childlike innocence and crucial role in the struggle between good and evil.
  • C. Tom Cullen chosen
    Tom Cullen is a British actor known for his roles in film and television, including prominent appearances in series like "Downton Abbey" and "Knightfall."
  • D. Tom Cullen
    Tom Cullen is an entrepreneur and business leader best known as a co-founder of the technology company Rincon Networks.
  • E. John Cullen
    John Cullen is a former professional ice hockey goaltender best known for his standout collegiate career with the Boston University Terriers and subsequent play in the NHL.
  • 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b48be0481909f4601b732424e5b completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:48 p.m.