Triple

T21641109
Position Surface form Disambiguated ID Type / Status
Subject Indian cuisine E534089 entity
Predicate hasDish P17589 FINISHED
Object upma
Upma is a popular South Indian breakfast dish made by cooking semolina with spices, vegetables, and aromatics to create a soft, savory porridge-like preparation.
 E1493599 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: upma | Statement: [Indian cuisine, hasDish, upma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: upma
Context triple: [Indian cuisine, hasDish, upma]
  • A. upma pesarattu
    Upma pesarattu is a popular Andhra breakfast dish consisting of a thin green gram dosa wrapped around a filling of savory semolina upma.
  • B. UPG
    UPG is the IATA airport code for Sultan Hasanuddin International Airport serving Makassar in South Sulawesi, Indonesia.
  • C. UP
    UP was a major South African political party that dominated the country’s politics for much of the mid-20th century before being displaced by the National Party.
  • D. UP
    UP is the IATA airline designator used by Bahamasair, the national flag carrier of the Bahamas.
  • E. UP
    UP is the standard reporting mark used to identify rail equipment owned or operated by the Union Pacific Railroad in North America.
  • 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: upma
Triple: [Indian cuisine, hasDish, upma]
Generated description
Upma is a popular South Indian breakfast dish made by cooking semolina with spices, vegetables, and aromatics to create a soft, savory porridge-like preparation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: upma
Target entity description: Upma is a popular South Indian breakfast dish made by cooking semolina with spices, vegetables, and aromatics to create a soft, savory porridge-like preparation.
  • A. upma pesarattu
    Upma pesarattu is a popular Andhra breakfast dish consisting of a thin green gram dosa wrapped around a filling of savory semolina upma.
  • B. UPG
    UPG is the IATA airport code for Sultan Hasanuddin International Airport serving Makassar in South Sulawesi, Indonesia.
  • C. UP
    UP is the standard reporting mark used to identify rail equipment owned or operated by the Union Pacific Railroad in North America.
  • D. UP
    UP was a major South African political party that dominated the country’s politics for much of the mid-20th century before being displaced by the National Party.
  • E. UP
    UP is the commonly used abbreviation for the University of Primorska, a public university based in the coastal region of Slovenia.
  • 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_69e0c465ae7481908577b7209fdb2a77 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef53917f3c81909e7f4074beecefd3 completed April 27, 2026, 12:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a0fa26ce8819082d7be817f48f518 completed May 17, 2026, 6:57 p.m.
NEDg Description generation batch_6a0a104f33a88190bb350607912d1c70 completed May 17, 2026, 7 p.m.
NED2 Entity disambiguation (via description) batch_6a0a10f51f2481908aa30fc58bb930e4 completed May 17, 2026, 7:03 p.m.
Created at: April 16, 2026, 6:35 p.m.