Triple

T966802
Position Surface form Disambiguated ID Type / Status
Subject Makar Sankranti E20854 entity
Predicate regionalName P14444 FINISHED
Object Maghi
Maghi is a regional name for the Hindu harvest festival of Makar Sankranti, particularly observed in parts of North India.
 E114662 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: Maghi | Statement: [Makar Sankranti, regionalName, Maghi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Maghi
Context triple: [Makar Sankranti, regionalName, Maghi]
  • A. Dhulandi
    Dhulandi is the vibrant second day of the Holi festival in India, celebrated with the playful throwing of colored powders and water.
  • B. Hazaragi
    Hazaragi is a variety of Persian primarily spoken by the Hazara people of central Afghanistan and surrounding regions, distinguished by its unique phonology and significant Turkic and Mongolic influences.
  • C. Shuah
    Shuah is a lesser-known son of the biblical patriarch Abraham, mentioned among the children he had with Keturah.
  • D. Dinarzad
    Dinarzad is a character in The Arabian Nights, known as Shahrazad’s younger sister who prompts her to tell stories each night to the king.
  • E. Magahi
    Magahi is an Eastern Indo-Aryan language spoken primarily in the Indian state of Bihar and surrounding regions.
  • 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: Maghi
Triple: [Makar Sankranti, regionalName, Maghi]
Generated description
Maghi is a regional name for the Hindu harvest festival of Makar Sankranti, particularly observed in parts of North India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Maghi
Target entity description: Maghi is a regional name for the Hindu harvest festival of Makar Sankranti, particularly observed in parts of North India.
  • A. Dhulandi
    Dhulandi is the vibrant second day of the Holi festival in India, celebrated with the playful throwing of colored powders and water.
  • B. Hazaragi
    Hazaragi is a variety of Persian primarily spoken by the Hazara people of central Afghanistan and surrounding regions, distinguished by its unique phonology and significant Turkic and Mongolic influences.
  • C. Shuah
    Shuah is a lesser-known son of the biblical patriarch Abraham, mentioned among the children he had with Keturah.
  • D. Dinarzad
    Dinarzad is a character in The Arabian Nights, known as Shahrazad’s younger sister who prompts her to tell stories each night to the king.
  • E. Magahi
    Magahi is an Eastern Indo-Aryan language spoken primarily in the Indian state of Bihar and surrounding regions.
  • 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_69a493b33d2c81909c52c369d3ca8436 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b75103688190a14342eef3842984 completed March 1, 2026, 10:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac17055f008190a5011d9b23bd3858 completed March 7, 2026, 12:16 p.m.
NEDg Description generation batch_69ac17c2e6f48190be6fce7f279957c4 completed March 7, 2026, 12:19 p.m.
NED2 Entity disambiguation (via description) batch_69ac1844acec81909859605d2421a588 completed March 7, 2026, 12:21 p.m.
Created at: March 1, 2026, 7:40 p.m.