Triple

T14044662
Position Surface form Disambiguated ID Type / Status
Subject Body of Proof E337926 entity
Predicate starring P1507 FINISHED
Object Sonja Sohn E735056 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: Sonja Sohn | Statement: [Body of Proof, starring, Sonja Sohn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sonja Sohn
Context triple: [Body of Proof, starring, Sonja Sohn]
  • A. Sonja Sohn chosen
    Sonja Sohn is an American actress and filmmaker best known for her role as Detective Kima Greggs on the acclaimed television series "The Wire."
  • B. Laura Sohn
    Laura Sohn is an American actress best known for her role as FBI agent Alina Park on the television series "The Blacklist."
  • C. Sandra Chung
    Sandra Chung is an American linguist known for her influential work on syntax, Austronesian languages, and the interface between grammar and semantics.
  • D. Myung-wha Chung
    Myung-wha Chung is a renowned South Korean cellist recognized for her international concert career and collaborations with major orchestras and chamber ensembles.
  • E. Linda Park
    Linda Park is a Korean-American actress best known for playing communications officer Hoshi Sato on the television series Star Trek: Enterprise.
  • 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_69d81c664e48819088cbd8f433aeffe5 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de312b94308190bd0961f5bc719c7b completed April 14, 2026, 12:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc34148348190a8c67e035646e431 completed May 6, 2026, 10:40 p.m.
Created at: April 9, 2026, 10:20 p.m.