Triple

T12207568
Position Surface form Disambiguated ID Type / Status
Subject StyleGAN E290872 entity
Predicate trainingDataset P21227 FINISHED
Object FFHQ
FFHQ (Flickr-Faces-HQ) is a high-quality, large-scale dataset of diverse human face images widely used for training and evaluating generative image models.
 E971757 NE FINISHED

Disambiguation candidates (3 decisions)

The exact options the model was shown at each disambiguation step, with the option it chose highlighted — the evidence behind this triple's disambiguated ids.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FFHQ
Context triple: [StyleGAN, trainingDataset, FFHQ]
  • A. CelebA
    CelebA is a large-scale face attributes dataset widely used in computer vision research for tasks like facial recognition, attribute prediction, and generative modeling.
  • B. LFW
    LFW is the IATA airport code for Lomé–Tokoin International Airport, the main airport serving Lomé, the capital of Togo.
  • C. Faces Distribution
    Faces Distribution is a film distribution company known for handling the release of independent and art-house films such as John Cassavetes’ works.
  • D. Faces Places
    Faces Places is a 2017 French documentary film co-directed by Agnès Varda and artist JR, in which they travel through rural France creating large-scale photographic portraits while reflecting on memory, community, and aging.
  • E. Faces
    Faces is a critically acclaimed 2014 mixtape by American rapper Mac Miller, known for its introspective lyrics, experimental production, and exploration of themes like addiction and mental health.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FFHQ
Target entity description: FFHQ (Flickr-Faces-HQ) is a high-quality, large-scale dataset of diverse human face images widely used for training and evaluating generative image models.
  • A. CelebA
    CelebA is a large-scale face attributes dataset widely used in computer vision research for tasks like facial recognition, attribute prediction, and generative modeling.
  • B. LFW
    LFW is the IATA airport code for Lomé–Tokoin International Airport, the main airport serving Lomé, the capital of Togo.
  • C. Faces Distribution
    Faces Distribution is a film distribution company known for handling the release of independent and art-house films such as John Cassavetes’ works.
  • D. Faces Places
    Faces Places is a 2017 French documentary film co-directed by Agnès Varda and artist JR, in which they travel through rural France creating large-scale photographic portraits while reflecting on memory, community, and aging.
  • E. Faces
    Faces is a critically acclaimed 2014 mixtape by American rapper Mac Miller, known for its introspective lyrics, experimental production, and exploration of themes like addiction and mental health.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: trainingDataset
Context triple: [StyleGAN, trainingDataset, FFHQ]
  • A. trainingDataSource
    Indicates the origin or provider from which the training data for a model or system is obtained.
  • B. trainingDataType
    Indicates the type or category of data used for training a model, system, or process.
  • C. trainingDatasetSize
    Indicates the number of data samples or instances used to train a model or system.
  • D. trainingPopulation
    Indicates that one entity serves as the group of individuals or instances used to train or develop another entity, typically a model, system, or process.
  • E. trainingDataIncludes chosen
    Indicates that one entity’s training dataset contains or incorporates the other entity as part of its data.
  • F. None of above.

Provenance (6 batches)

Stage Batch ID Job type Status
creating batch_69d6ab65923081909acfc61b7a612233 elicitation completed
NER batch_69d920e312708190b4aede2e21f5f697 ner completed
NED1 batch_69f60a9d2f0c81908352cd9f0167c6ab ned_source_triple completed
NED2 batch_69f60fe8c2ec8190af7c69dd17ea75fe ned_description completed
NEDg batch_69f60f2154c8819081f9cf6f51e5255b nedg completed
PD batch_69d91c3d669c81908eea7ad61122d275 pd completed
Created at: April 8, 2026, 9:51 p.m.