Triple

T22052726
Position Surface form Disambiguated ID Type / Status
Subject Fuji Television Network, Inc. E544923 entity
Predicate memberOf P10 FINISHED
Object FNN
FNN is a Japanese commercial television news network centered around Fuji Television that provides national news programming through its affiliated stations.
 E1516143 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: FNN | Statement: [Fuji Television Network, Inc., memberOf, FNN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FNN
Context triple: [Fuji Television Network, Inc., memberOf, FNN]
  • A. FNN
    FNN is the three-letter National Rail station code assigned to Farnborough North railway station in Hampshire, England.
  • B. DNN
    DNN is the stock ticker symbol for Denison Mines Corp., a Canadian uranium exploration and development company.
  • C. NN
    NN is the postcode area in the United Kingdom that covers Northampton and surrounding parts of Northamptonshire.
  • D. FCN
    FCN is the common abbreviation for 1. FC Nürnberg, a German football club based in Nuremberg.
  • E. deep feedforward networks
    Deep feedforward networks are a class of neural network architectures in which information flows in one direction through multiple layers to learn complex input–output mappings without recurrent connections.
  • 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: FNN
Triple: [Fuji Television Network, Inc., memberOf, FNN]
Generated description
FNN is a Japanese commercial television news network centered around Fuji Television that provides national news programming through its affiliated stations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FNN
Target entity description: FNN is a Japanese commercial television news network centered around Fuji Television that provides national news programming through its affiliated stations.
  • A. FNN
    FNN is the three-letter National Rail station code assigned to Farnborough North railway station in Hampshire, England.
  • B. DNN
    DNN is the stock ticker symbol for Denison Mines Corp., a Canadian uranium exploration and development company.
  • C. NN
    NN is the postcode area in the United Kingdom that covers Northampton and surrounding parts of Northamptonshire.
  • D. FCN
    FCN is the common abbreviation for 1. FC Nürnberg, a German football club based in Nuremberg.
  • E. deep feedforward networks
    Deep feedforward networks are a class of neural network architectures in which information flows in one direction through multiple layers to learn complex input–output mappings without recurrent connections.
  • F. None of above. chosen

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_69e11e3377c48190890c17407b9527d6 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1285513fc8190b691e1f57085956f completed April 28, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a7b7b3ccc8190a4d8728b135aa22d completed May 18, 2026, 2:37 a.m.
NEDg Description generation batch_6a0a7c2705e48190aebbc7b0b6221757 completed May 18, 2026, 2:40 a.m.
NED2 Entity disambiguation (via description) batch_6a0a7ce3c684819090b25ca1e7596722 completed May 18, 2026, 2:43 a.m.
Created at: April 16, 2026, 8:26 p.m.