Triple

T19638941
Position Surface form Disambiguated ID Type / Status
Subject Harishena E471476 entity
Predicate capital P234 FINISHED
Object Vatsagulma
Vatsagulma was an ancient city in central India that served as an important Vakataka royal center and the seat of King Harishena’s power.
 E1387523 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: Vatsagulma | Statement: [Harishena, capital, Vatsagulma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vatsagulma
Context triple: [Harishena, capital, Vatsagulma]
  • A. Yudgha
    Yudgha is an alternative name for Yidgha, an Eastern Iranian language spoken primarily in the Chitral region of northern Pakistan.
  • B. Manthara
    Manthara is a pivotal character in the Indian epic Ramayana, known as Queen Kaikeyi’s scheming maid whose manipulation leads to Rama’s exile.
  • C. Sakhuwaprasauni
    Sakhuwaprasauni is a locality in Nepal situated within Madhesh Province, known as part of the country’s southeastern Terai region.
  • D. Vidhaata
    Vidhaata is a 1982 Hindi action drama film directed by Subhash Ghai, known for its star-studded cast, popular music, and commercial success in Indian cinema.
  • E. Lavanasura
    Lavanasura is a demon king in Hindu mythology, known primarily as a formidable adversary defeated by Shatrughna, the younger brother of Lord Rama.
  • 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: Vatsagulma
Triple: [Harishena, capital, Vatsagulma]
Generated description
Vatsagulma was an ancient city in central India that served as an important Vakataka royal center and the seat of King Harishena’s power.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vatsagulma
Target entity description: Vatsagulma was an ancient city in central India that served as an important Vakataka royal center and the seat of King Harishena’s power.
  • A. Yudgha
    Yudgha is an alternative name for Yidgha, an Eastern Iranian language spoken primarily in the Chitral region of northern Pakistan.
  • B. Manthara
    Manthara is a pivotal character in the Indian epic Ramayana, known as Queen Kaikeyi’s scheming maid whose manipulation leads to Rama’s exile.
  • C. Sakhuwaprasauni
    Sakhuwaprasauni is a locality in Nepal situated within Madhesh Province, known as part of the country’s southeastern Terai region.
  • D. Vidhaata
    Vidhaata is a 1982 Hindi action drama film directed by Subhash Ghai, known for its star-studded cast, popular music, and commercial success in Indian cinema.
  • E. Lavanasura
    Lavanasura is a demon king in Hindu mythology, known primarily as a formidable adversary defeated by Shatrughna, the younger brother of Lord Rama.
  • 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e641090c408190b2adb8a6abf1b4c9 completed April 20, 2026, 3:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a077ee4e2e08190a3f9faa22402817f completed May 15, 2026, 8:15 p.m.
NEDg Description generation batch_6a077f74e4fc81909fd1c65af64ba68f completed May 15, 2026, 8:17 p.m.
NED2 Entity disambiguation (via description) batch_6a0780e305f08190805e21212dec0b39 completed May 15, 2026, 8:24 p.m.
Created at: April 10, 2026, 1:44 p.m.