Triple

T5532899
Position Surface form Disambiguated ID Type / Status
Subject Mercury Plains E145090 entity
Predicate starring P1507 FINISHED
Object Angela Sarafyan E385511 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: Angela Sarafyan | Statement: [Mercury Plains, starring, Angela Sarafyan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Angela Sarafyan
Context triple: [Mercury Plains, starring, Angela Sarafyan]
  • A. Angela Sarafyan chosen
    Angela Sarafyan is an Armenian-American actress known for her roles in film and television, including notable performances in projects like HBO's "Westworld."
  • B. Katherine Sarafian
    Katherine Sarafian is an American film producer best known for her work at Pixar Animation Studios, including producing the Academy Award–winning feature "Brave."
  • C. Evangeline Mardirosian
    Evangeline Mardirosian is a film producer known for her co-producing work on the movie "Daytona."
  • D. Tedi Sarafian
    Tedi Sarafian is an American screenwriter and film producer best known for his work on major action and science fiction films.
  • E. Isabel Bayrakdarian
    Isabel Bayrakdarian is an Armenian-Canadian operatic soprano acclaimed for her performances on international stages and her diverse repertoire spanning opera, concert, and recording projects.
  • 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_69c008f9955881909bfa8348b56b4739 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01f9ea2c88190a68642f5799bd8ff completed March 22, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0280cb42c8190bf5ba546aca5edce completed March 22, 2026, 5:34 p.m.
Created at: March 22, 2026, 3:34 p.m.