Triple

T8415928
Position Surface form Disambiguated ID Type / Status
Subject Omnicom Group E198729 entity
Predicate hasSubsidiary P254 FINISHED
Object RAPP
RAPP is a global marketing and customer experience agency known for its data-driven, personalized communications and direct marketing services.
 E733015 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: RAPP | Statement: [Omnicom Group, hasSubsidiary, RAPP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: RAPP
Context triple: [Omnicom Group, hasSubsidiary, RAPP]
  • A. Rapp and Rapp
    Rapp and Rapp was a prominent early 20th-century American architectural firm best known for designing lavish movie palaces and theaters across the United States.
  • B. Rappen
    Rappen is the German term for the centime-like subunit of the Swiss franc, used to denote its smaller denominations.
  • C. RAP
    RAP is the standard abbreviation used for Raptors 905, the NBA G League affiliate of the Toronto Raptors.
  • D. Raus
    Raus is a German-language surname most notably associated with Erhard Raus, a high-ranking Wehrmacht general during World War II.
  • E. RANC
    RANC is the Royal Australian Navy’s principal officer training institution, responsible for educating and preparing naval officers for service.
  • 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: RAPP
Triple: [Omnicom Group, hasSubsidiary, RAPP]
Generated description
RAPP is a global marketing and customer experience agency known for its data-driven, personalized communications and direct marketing services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: RAPP
Target entity description: RAPP is a global marketing and customer experience agency known for its data-driven, personalized communications and direct marketing services.
  • A. Rapp and Rapp
    Rapp and Rapp was a prominent early 20th-century American architectural firm best known for designing lavish movie palaces and theaters across the United States.
  • B. Rappen
    Rappen is the German term for the centime-like subunit of the Swiss franc, used to denote its smaller denominations.
  • C. RAP
    RAP is the standard abbreviation used for Raptors 905, the NBA G League affiliate of the Toronto Raptors.
  • D. Raus
    Raus is a German-language surname most notably associated with Erhard Raus, a high-ranking Wehrmacht general during World War II.
  • E. RANC
    RANC is the Royal Australian Navy’s principal officer training institution, responsible for educating and preparing naval officers for service.
  • 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_69ca831201b481909e137936ef99ff11 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cb84c5121081908efa3eca25406d3a completed March 31, 2026, 8:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce0333a3488190ba30d03b1d7bacb1 completed April 2, 2026, 5:48 a.m.
NEDg Description generation batch_69ce0781859c8190bb92f41c00af459b completed April 2, 2026, 6:06 a.m.
NED2 Entity disambiguation (via description) batch_69ce089d09c08190ba321aed4044a862 completed April 2, 2026, 6:11 a.m.
Created at: March 30, 2026, 6:06 p.m.