Triple

T13304597
Position Surface form Disambiguated ID Type / Status
Subject Joe Mantell E316903 entity
Predicate quoteFrom P21904 FINISHED
Object Marty E51894 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: Marty | Statement: [Joe Mantell, quoteFrom, Marty]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marty
Context triple: [Joe Mantell, quoteFrom, Marty]
  • A. Marty chosen
    Marty is a 1955 American romantic drama film that won the Academy Award for Best Picture and is renowned for its poignant portrayal of a lonely butcher’s search for love.
  • B. Marty
    Marty is a central character in the 1996 ensemble drama film "Beautiful Girls," known for her youthful charm and pivotal role in the story’s exploration of love and growing up.
  • C. Marty
    Marty is a common diminutive form of the given name Martin, often used as a familiar or informal nickname.
  • D. Marty
    Marty is a common diminutive form of the given name Martha.
  • E. Marty
    Marty is a surname of French origin, notably borne by figures such as André Marty, a prominent French communist and political activist.
  • 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: quoteFrom
Context triple: [Joe Mantell, quoteFrom, Marty]
  • A. quoteLanguage
    Indicates that a quoted text is expressed in a particular language.
  • B. quoteProvision
    Indicates that one entity supplies or presents a quotation or price estimate to another entity.
  • C. quotedOn
    Indicates that one entity is cited, referenced, or mentioned within another source, document, or context.
  • D. quotationText
    Indicates that the associated text is the exact content of a quotation made or referenced in the relationship.
  • E. quoteAttributedTo chosen
    Indicates that a specific quotation is credited as having been said or written by a particular source or entity.
  • 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_69d806b40ab4819094adf6c374f4811a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d99cfdc9388190af1fdd3cd4717bd8 completed April 11, 2026, 12:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7305fd57881909c1d7f09f3c084cf completed May 3, 2026, 11:24 a.m.
PD Predicate disambiguation batch_69d98f6893708190aeebf4c47386cff7 completed April 11, 2026, 12:01 a.m.
Created at: April 9, 2026, 9:28 p.m.