Triple

T8353948
Position Surface form Disambiguated ID Type / Status
Subject Grace Coddington E196630 entity
Predicate hasGivenName P17 FINISHED
Object Grace
Grace is the given name of Grace Coddington, the influential former model and longtime creative director of American Vogue.
E295685 NE FINISHED

How this triple was built (4 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: Grace | Statement: [Grace Coddington, hasGivenName, Grace]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grace
Context triple: [Grace Coddington, hasGivenName, Grace]
  • A. Grace
    Grace is the central Christian concept of God’s unmerited favor and loving initiative toward humanity, enabling salvation and spiritual transformation.
  • B. Grace
    "Grace" is a song by the Irish rock band U2 from their 2000 album *All That You Can’t Leave Behind*.
  • C. Grace
    "Grace" is a British crime drama television series starring John Simm as Detective Superintendent Roy Grace, adapted from Peter James's bestselling novels.
  • D. Grace
    "Grace" is a popular contemporary gospel album by Tasha Cobbs known for its powerful worship songs and breakout hit "Break Every Chain."
  • E. Grace
    Grace is Jeff Buckley’s acclaimed 1994 debut studio album, celebrated for its emotive vocals, eclectic songwriting, and enduring influence on alternative rock.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Grace
Triple: [Grace Coddington, hasGivenName, Grace]
Generated description
Grace is the given name of Grace Coddington, the influential former model and longtime creative director of American Vogue.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Grace
Target entity description: Grace is the given name of Grace Coddington, the influential former model and longtime creative director of American Vogue.
  • A. Grace chosen
    Grace is a feminine given name of Latin origin meaning "grace" or "favor," often associated with elegance and kindness.
  • B. Grace
    "Grace" is a popular contemporary gospel album by Tasha Cobbs known for its powerful worship songs and breakout hit "Break Every Chain."
  • C. Grace
    Grace is the central Christian concept of God’s unmerited favor and loving initiative toward humanity, enabling salvation and spiritual transformation.
  • D. Grace
    Grace is Jeff Buckley’s acclaimed 1994 debut studio album, celebrated for its emotive vocals, eclectic songwriting, and enduring influence on alternative rock.
  • E. Grace
    Grace is a skilled and enigmatic thief who becomes entangled with Ethan Hunt and the IMF team in the action film "Mission: Impossible – Dead Reckoning Part One."
  • F. None of above.

Provenance (5 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_69ca82f08b348190bfb7881944bbff6f completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb804756088190a766e1a486ccfdff completed March 31, 2026, 8:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69cdc75e94288190ba1905dd4ca172dd completed April 2, 2026, 1:33 a.m.
NEDg Description generation batch_69cdcc86626c8190a4206feedea24b41 completed April 2, 2026, 1:55 a.m.
NED2 Entity disambiguation (via description) batch_69cdcde02e088190be8220f7d18d6700 completed April 2, 2026, 2:01 a.m.
Created at: March 30, 2026, 5:59 p.m.