Triple

T23467293
Position Surface form Disambiguated ID Type / Status
Subject Sharma E569129 entity
Predicate hasVariant P455 FINISHED
Object Sarmah
Sarmah is an alternative spelling or variant of the Indian surname Sharma, commonly found in parts of South Asia.
 E1589865 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: Sarmah | Statement: [Sharma, hasVariant, Sarmah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sarmah
Context triple: [Sharma, hasVariant, Sarmah]
  • A. Sarayan
    Sarayan is a small city in eastern Iran known as an administrative and agricultural center within South Khorasan Province.
  • B. Soura
    Soura is an indigenous tribal community of eastern India, known for its distinct language, traditional art, and hill-based agrarian lifestyle.
  • C. Sakia
    Sakia is a prominent cultural center and arts venue in Cairo, Egypt, known for hosting concerts, exhibitions, and a wide range of cultural events.
  • D. Sangemarmar Sar
    Sangemarmar Sar is a high, glaciated mountain peak in the Batura Muztagh subrange of the Karakoram in northern Pakistan.
  • E. Sohawa
    Sohawa is a town in Pakistan’s Punjab province that serves as an important local center within the Jhelum District.
  • 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: Sarmah
Triple: [Sharma, hasVariant, Sarmah]
Generated description
Sarmah is an alternative spelling or variant of the Indian surname Sharma, commonly found in parts of South Asia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sarmah
Target entity description: Sarmah is an alternative spelling or variant of the Indian surname Sharma, commonly found in parts of South Asia.
  • A. Sarayan
    Sarayan is a small city in eastern Iran known as an administrative and agricultural center within South Khorasan Province.
  • B. Soura
    Soura is an indigenous tribal community of eastern India, known for its distinct language, traditional art, and hill-based agrarian lifestyle.
  • C. Sakia
    Sakia is a prominent cultural center and arts venue in Cairo, Egypt, known for hosting concerts, exhibitions, and a wide range of cultural events.
  • D. Sangemarmar Sar
    Sangemarmar Sar is a high, glaciated mountain peak in the Batura Muztagh subrange of the Karakoram in northern Pakistan.
  • E. Sohawa
    Sohawa is a town in Pakistan’s Punjab province that serves as an important local center within the Jhelum District.
  • 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_69e2458ebd808190b3298163132cfb0b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a6fc35c48190a67614fb4170f15b completed April 29, 2026, 6:36 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c8254f3fc819098b6b59eb19e27f0 completed May 19, 2026, 3:31 p.m.
NEDg Description generation batch_6a0ca6efb0d88190bf15b18cc3f12482 completed May 19, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0ca819f6dc8190852bb3c06768ac5a completed May 19, 2026, 6:12 p.m.
Created at: April 17, 2026, 5:54 p.m.