Triple

T2236748
Position Surface form Disambiguated ID Type / Status
Subject Nuristan Province E49298 entity
Predicate capital P234 FINISHED
Object Parun
Parun is a small town in eastern Afghanistan that serves as the administrative and political center of Nuristan Province.
 E248496 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: Parun | Statement: [Nuristan Province, capital, Parun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Parun
Context triple: [Nuristan Province, capital, Parun]
  • A. Parushni
    Parushni is the ancient Vedic name for the Ravi River, one of the major rivers of the northwestern Indian subcontinent.
  • B. Porul
    Porul is the second section of the ancient Tamil classic Tirukkural, focusing on ethics, governance, politics, and social conduct.
  • C. Parva
    Parva is a renowned Kannada novel by S. L. Bhyrappa that offers a modern, realistic retelling of the Indian epic Mahabharata.
  • D. Prasuni
    Prasuni is a Nuristani language spoken by a small community in the remote valleys of eastern Afghanistan.
  • E. Peremoun
    Peremoun is an alternative name for Pelusium, an ancient Egyptian city located near the easternmost branch of the Nile Delta that served as a key frontier fortress and trade hub.
  • 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: Parun
Triple: [Nuristan Province, capital, Parun]
Generated description
Parun is a small town in eastern Afghanistan that serves as the administrative and political center of Nuristan Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Parun
Target entity description: Parun is a small town in eastern Afghanistan that serves as the administrative and political center of Nuristan Province.
  • A. Parushni
    Parushni is the ancient Vedic name for the Ravi River, one of the major rivers of the northwestern Indian subcontinent.
  • B. Porul
    Porul is the second section of the ancient Tamil classic Tirukkural, focusing on ethics, governance, politics, and social conduct.
  • C. Parva
    Parva is a renowned Kannada novel by S. L. Bhyrappa that offers a modern, realistic retelling of the Indian epic Mahabharata.
  • D. Prasuni
    Prasuni is a Nuristani language spoken by a small community in the remote valleys of eastern Afghanistan.
  • E. Peremoun
    Peremoun is an alternative name for Pelusium, an ancient Egyptian city located near the easternmost branch of the Nile Delta that served as a key frontier fortress and trade hub.
  • 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_69a88aa84bdc819086df50e9c20b301e completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc09573848190bf91eddcc2fa0061 completed March 7, 2026, 6:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6b08c5248190924a28f4c1bd0e2c completed March 9, 2026, 6:39 a.m.
NEDg Description generation batch_69ae6c5cb33481909261f7010e8e21a6 completed March 9, 2026, 6:44 a.m.
NED2 Entity disambiguation (via description) batch_69ae6cd61e808190aefca4d4aa1f8e39 completed March 9, 2026, 6:46 a.m.
Created at: March 4, 2026, 7:47 p.m.