Triple

T1790849
Position Surface form Disambiguated ID Type / Status
Subject Air (2023 film) E39490 entity
Predicate starring P1507 FINISHED
Object Ben Affleck E40496 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: Ben Affleck | Statement: [Air (2023 film), starring, Ben Affleck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ben Affleck
Context triple: [Air (2023 film), starring, Ben Affleck]
  • A. Ben Affleck chosen
    Ben Affleck is an American actor, director, and screenwriter known for films such as "Good Will Hunting," "Argo," and for portraying Batman in the DC Extended Universe.
  • B. Matt Damon
    Matt Damon is an American actor, producer, and screenwriter known for his versatile performances in films such as Good Will Hunting, the Bourne series, and The Martian.
  • C. Afflecks
    Afflecks is an iconic indoor market and alternative shopping emporium in Manchester known for its independent retailers, vintage fashion, and vibrant subcultural atmosphere.
  • D. Michael Wahlberg
    Michael Wahlberg is one of the children of American actor, producer, and former rapper Mark Wahlberg.
  • E. Mark Wahlberg
    Mark Wahlberg is an American actor and producer known for his roles in films such as "Boogie Nights," "The Departed," and the "Transformers" series, as well as for his earlier career as a rapper under the name Marky Mark.
  • 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_69a88631854081909723959921e45c2b completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa6512804c8190a5743c10bd37f83f completed March 6, 2026, 5:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae5d7d1f6c8190a1033c784091ffb8 completed March 9, 2026, 5:41 a.m.
Created at: March 4, 2026, 7:32 p.m.