Triple

T23251389
Position Surface form Disambiguated ID Type / Status
Subject Rai Movie E581738 entity
Predicate hasSisterChannel P6991 FINISHED
Object Rai 5
Rai 5 is an Italian public television channel from the RAI network focused on culture, arts, documentaries, and highbrow entertainment programming.
 E140861 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: Rai 5 | Statement: [Rai Movie, hasSisterChannel, Rai 5]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rai 5
Context triple: [Rai Movie, hasSisterChannel, Rai 5]
  • A. RAI
    RAI is the station code for Station RAI, a railway stop identified by this three-letter abbreviation.
  • B. RAI
    RAI is the national state-owned railway company responsible for operating and managing Iran’s rail transport network.
  • C. RAI
    RAI is the stock ticker symbol for Reynolds American Inc., a major U.S. tobacco company known for brands like Camel and Newport.
  • D. RAI
    RAI is the IATA airport code for Nelson Mandela International Airport, the main airport serving Praia in Cape Verde.
  • E. RAI
    RAI is a leading British scholarly society dedicated to the study and promotion of anthropology and related disciplines.
  • 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: Rai 5
Triple: [Rai Movie, hasSisterChannel, Rai 5]
Generated description
Rai 5 is an Italian public television channel from the RAI network focused on culture, arts, documentaries, and highbrow entertainment programming.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rai 5
Target entity description: Rai 5 is an Italian public television channel from the RAI network focused on culture, arts, documentaries, and highbrow entertainment programming.
  • A. RAI
    RAI is the station code for Station RAI, a railway stop identified by this three-letter abbreviation.
  • B. RAI
    RAI is the national state-owned railway company responsible for operating and managing Iran’s rail transport network.
  • C. RAI chosen
    RAI is Italy’s national public broadcasting company, operating multiple television and radio channels and producing a wide range of news, entertainment, and cultural programming.
  • D. RAI
    RAI is the stock ticker symbol for Reynolds American Inc., a major U.S. tobacco company known for brands like Camel and Newport.
  • E. RAI
    RAI is the IATA airport code for Nelson Mandela International Airport, the main airport serving Praia in Cape Verde.
  • 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_69e24606b17c81908aba1a4911c8a8ba completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f193f7249481909424867e9542d35e completed April 29, 2026, 5:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0cdf2ad70881909a287c5771a38f5d completed May 19, 2026, 10:07 p.m.
NEDg Description generation batch_6a0ce1b65028819085db361355416229 completed May 19, 2026, 10:18 p.m.
NED2 Entity disambiguation (via description) batch_6a0ce22ac5ac8190b708bb201fdf3af8 completed May 19, 2026, 10:20 p.m.
Created at: April 17, 2026, 4:10 p.m.