Triple

T22090925
Position Surface form Disambiguated ID Type / Status
Subject Marshall E545909 entity
Predicate writer P1360 FINISHED
Object Jacob Koskoff 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: Jacob Koskoff | Statement: [Marshall, writer, Jacob Koskoff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jacob Koskoff
Context triple: [Marshall, writer, Jacob Koskoff]
  • A. Jacob Koskoff chosen
    Jacob Koskoff is an American screenwriter best known for co-writing the 2015 film adaptation of Shakespeare’s "Macbeth."
  • B. Michael Koskoff
    Michael Koskoff was an American trial lawyer and author best known for co-writing the historical legal drama film "Marshall."
  • C. Jacob Kasher
    Jacob Kasher is an American songwriter and producer known for crafting pop hits for major artists such as Maroon 5, One Direction members, and Charlie Puth.
  • D. Jeremy Gelbwaks
    Jeremy Gelbwaks is an American former child actor best known for originating the role of Chris Partridge on the early 1970s television sitcom "The Partridge Family."
  • E. Marc Roskin
    Marc Roskin is a television producer and director best known for his work on genre and adventure series such as "The Librarians."
  • 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_69e11e36d03c8190a83a1ba802b7231b completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128e53dfc81909858cdad8b09c5fb completed April 28, 2026, 9:38 p.m.
Created at: April 16, 2026, 8:29 p.m.