Triple

T2461384
Position Surface form Disambiguated ID Type / Status
Subject Manchester by the Sea E54540 entity
Predicate supportingActress P8120 FINISHED
Object Michelle Williams E38536 NE FINISHED

How this triple was built (3 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: Michelle Williams | Statement: [Manchester by the Sea, supportingActress, Michelle Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michelle Williams
Context triple: [Manchester by the Sea, supportingActress, Michelle Williams]
  • A. Michelle Williams chosen
    Michelle Williams is an acclaimed American actress known for her emotionally nuanced performances in both independent films and major studio productions, earning multiple Academy Award and Golden Globe nominations and wins.
  • B. Michelle Williams
    Michelle Williams is an American singer and actress best known as one of the lead vocalists of the Grammy-winning R&B group Destiny's Child.
  • C. Rachel McAdams
    Rachel McAdams is a Canadian actress known for her versatile performances in films such as "Mean Girls," "The Notebook," and "Spotlight."
  • D. Jessica Rains
    Jessica Rains is an American actress and producer, best known as the daughter of acclaimed British actor Claude Rains and for her work in film and television during the late 20th century.
  • E. Elizabeth Perkins
    Elizabeth Perkins is an American actress known for her versatile film and television roles, including work in both live-action and animated projects.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: supportingActress
Context triple: [Manchester by the Sea, supportingActress, Michelle Williams]
  • A. supportingActressNominee
    Indicates that a person has been nominated for an award in the category of supporting actress.
  • B. bestSupportingActressWinner
    Indicates that the subject is the person who won the Best Supporting Actress award for the specified work, year, or event.
  • C. bestSupportingActressFilm chosen
    Indicates the film for which a person received or was nominated for a Best Supporting Actress award.
  • D. bestSupportingActorFilm
    Indicates the film for which a person received the Best Supporting Actor award.
  • E. bestSupportingActorWinner
    Indicates that an entity has received the award for Best Supporting Actor for a particular work or event.
  • F. None of above.

Provenance (4 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_69ab49dee84c819096b50a0049c347ac completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd49c5aa081909ab4f726a458b77f completed March 7, 2026, 7:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69af654726988190a7166434ecf0582c completed March 10, 2026, 12:26 a.m.
PD Predicate disambiguation batch_69abd0b199488190aa381b36593ae1ac completed March 7, 2026, 7:16 a.m.
Created at: March 6, 2026, 9:44 p.m.