Triple

T237002
Position Surface form Disambiguated ID Type / Status
Subject Assam E4843 entity
Predicate traditionalInstrument P8530 FINISHED
Object Pepa
Pepa is a traditional Assamese wind instrument, typically made from buffalo horn, used in folk and Bihu music.
 E32157 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: Pepa | Statement: [Assam, traditionalInstrument, Pepa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pepa
Context triple: [Assam, traditionalInstrument, Pepa]
  • A. Pablo
    Pablo is a given name, especially common in Spanish-speaking countries, that corresponds to the English name Paul.
  • B. Jorge
    Jorge is the birth name of Pope Francis, the head of the Roman Catholic Church and the first pope from the Americas.
  • C. Fifi
    Fifi was one of Jane Goodall’s most closely observed wild chimpanzees at Gombe, known for her long-term presence in the study and her role in revealing chimpanzee social and family dynamics.
  • D. Roberto
    Roberto is a masculine given name commonly used in Romance-language countries, equivalent to the English name Robert.
  • E. Emil
    Emil is the given name of Carl Gustaf Emil Mannerheim, the renowned Finnish military leader and statesman who served as President of Finland.
  • 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: Pepa
Triple: [Assam, traditionalInstrument, Pepa]
Generated description
Pepa is a traditional Assamese wind instrument, typically made from buffalo horn, used in folk and Bihu music.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pepa
Target entity description: Pepa is a traditional Assamese wind instrument, typically made from buffalo horn, used in folk and Bihu music.
  • A. Pablo
    Pablo is a given name, especially common in Spanish-speaking countries, that corresponds to the English name Paul.
  • B. Jorge
    Jorge is the birth name of Pope Francis, the head of the Roman Catholic Church and the first pope from the Americas.
  • C. Fifi
    Fifi was one of Jane Goodall’s most closely observed wild chimpanzees at Gombe, known for her long-term presence in the study and her role in revealing chimpanzee social and family dynamics.
  • D. Roberto
    Roberto is a masculine given name commonly used in Romance-language countries, equivalent to the English name Robert.
  • E. Emil
    Emil is the given name of Carl Gustaf Emil Mannerheim, the renowned Finnish military leader and statesman who served as President of Finland.
  • 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_69a257c3d0708190b0871c4269d273e6 completed Feb. 28, 2026, 2:49 a.m.
NER Named-entity recognition batch_69a260c42060819089eb772202e504f5 completed Feb. 28, 2026, 3:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3736e4010819089000ed60dbf519c completed Feb. 28, 2026, 10:59 p.m.
NEDg Description generation batch_69a373c9a698819088b3981ffbf85f9b completed Feb. 28, 2026, 11:01 p.m.
NED2 Entity disambiguation (via description) batch_69a3742d7efc81908a46e928326e43fa completed Feb. 28, 2026, 11:03 p.m.
Created at: Feb. 28, 2026, 2:53 a.m.