Triple

T23481561
Position Surface form Disambiguated ID Type / Status
Subject Poseidon (2006 film) E570418 entity
Predicate starredActor P5563 FINISHED
Object Emmy Rossum 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: Emmy Rossum | Statement: [Poseidon (2006 film), starredActor, Emmy Rossum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emmy Rossum
Context triple: [Poseidon (2006 film), starredActor, Emmy Rossum]
  • A. Emmy Rossum chosen
    Emmy Rossum is an American actress and singer best known for her role as Fiona Gallagher on the TV series "Shameless" and for her work in films such as "The Phantom of the Opera."
  • B. Shailene Woodley
    Shailene Woodley is an American actress known for her breakout role in "The Descendants" and for starring in films such as "The Fault in Our Stars" and the "Divergent" series.
  • C. Kristen Stewart
    Kristen Stewart is an American actress best known for her role as Bella Swan in the "Twilight" film series and for her acclaimed performances in independent and arthouse films.
  • D. Hanna Langlet
    Hanna Langlet was a 19th-century Swedish woman known primarily as the wife of architect Emil Victor Langlet.
  • E. Jena Malone
    Jena Malone is an American actress and musician known for her versatile roles in independent films and major franchises such as "Donnie Darko," "Pride & Prejudice," and "The Hunger Games" series.
  • 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_69e245b0b01481908f636939bedd804c completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a75002008190b02fbffd94e5e8b1 completed April 29, 2026, 6:38 a.m.
Created at: April 17, 2026, 6:03 p.m.