Triple

T12877332
Position Surface form Disambiguated ID Type / Status
Subject Face/Off E308001 entity
Predicate writer P1360 FINISHED
Object Mike Werb E524243 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: Mike Werb | Statement: [Face/Off, writer, Mike Werb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mike Werb
Context triple: [Face/Off, writer, Mike Werb]
  • A. Mike Werb chosen
    Mike Werb is an American screenwriter best known for co-writing high-concept Hollywood films such as "Face/Off" and "The Mask."
  • B. Brian Yablonski
    Brian Yablonski is a conservation-focused public policy leader and writer known for his work on wildlife, land stewardship, and free-market environmentalism.
  • C. Mike Nussbaum
    Mike Nussbaum is an American actor and director known for his character roles in film, television, and theater, including work in David Mamet projects such as "House of Games."
  • D. Phil DeVoss
    Phil DeVoss is a fictional character from the romantic comedy-drama film "Elizabethtown," which explores themes of family, failure, and self-discovery.
  • E. Kevin Weisman
    Kevin Weisman is an American character actor best known for his role as Marshall Flinkman on the television series "Alias" and for numerous appearances in film and television comedies and dramas.
  • 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_69d7bdf69bc48190af6c2621f28ca351 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d970fa8474819086a8af3c90f3ca84 completed April 10, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8ccee708190bb4caa604386e3a3 completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 5:38 p.m.