Triple

T23562772
Position Surface form Disambiguated ID Type / Status
Subject Agnimitra E579286 entity
Predicate spouse P13 FINISHED
Object Dharini
Dharini is known in ancient Indian history and legend as the wife of King Agnimitra of the Shunga dynasty.
 E1590052 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: Dharini | Statement: [Agnimitra, spouse, Dharini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dharini
Context triple: [Agnimitra, spouse, Dharini]
  • A. Dhara
    Dhara was the historic capital city of the Paramara dynasty in central India, known as an important political and cultural center during the medieval period.
  • B. Indrayani
    Indrayani is a figure from Hindu tradition known primarily as the wife of the sage-warrior Parashurama, an incarnation of the god Vishnu.
  • C. Vaidehi
    Vaidehi is an epithet of Sita, the revered heroine of the Hindu epic Ramayana and wife of Lord Rama.
  • D. Amritha
    Amritha is a given name, typically used as a variant spelling of the Indian name Amrita, which means “immortal” or “nectar” in Sanskrit.
  • E. Dharni
    Dharni is a small town in the Amravati district of Maharashtra, India, known as a local administrative and market center for surrounding rural and tribal areas.
  • 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: Dharini
Triple: [Agnimitra, spouse, Dharini]
Generated description
Dharini is known in ancient Indian history and legend as the wife of King Agnimitra of the Shunga dynasty.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dharini
Target entity description: Dharini is known in ancient Indian history and legend as the wife of King Agnimitra of the Shunga dynasty.
  • A. Dhara
    Dhara was the historic capital city of the Paramara dynasty in central India, known as an important political and cultural center during the medieval period.
  • B. Indrayani
    Indrayani is a figure from Hindu tradition known primarily as the wife of the sage-warrior Parashurama, an incarnation of the god Vishnu.
  • C. Vaidehi
    Vaidehi is an epithet of Sita, the revered heroine of the Hindu epic Ramayana and wife of Lord Rama.
  • D. Amritha
    Amritha is a given name, typically used as a variant spelling of the Indian name Amrita, which means “immortal” or “nectar” in Sanskrit.
  • E. Dharni
    Dharni is a small town in the Amravati district of Maharashtra, India, known as a local administrative and market center for surrounding rural and tribal areas.
  • 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_69e245fe24588190888f3aec8407d8e3 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1af6a02208190b7d35c4e5da67a44 completed April 29, 2026, 7:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0cdf6d367c81908469168fcff80c31 completed May 19, 2026, 10:08 p.m.
NEDg Description generation batch_6a0ce05e81a0819089f23092f0650f44 completed May 19, 2026, 10:12 p.m.
NED2 Entity disambiguation (via description) batch_6a0ce0db395c819090411d5871bd253f completed May 19, 2026, 10:14 p.m.
Created at: April 17, 2026, 6:25 p.m.