Triple

T4512336
Position Surface form Disambiguated ID Type / Status
Subject Ancient India E102079 entity
Predicate notableRuler P22 FINISHED
Object Harsha
Harsha was a 7th-century Indian emperor who unified much of northern India and became renowned for his patronage of Buddhism, literature, and the arts.
 E448492 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: Harsha | Statement: [Ancient India, notableRuler, Harsha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Harsha
Context triple: [Ancient India, notableRuler, Harsha]
  • A. Harish
    Harish is the given name of Harish-Chandra, a prominent Indian-American mathematician and physicist known for his foundational work in representation theory.
  • B. Vikram
    Vikram is a prominent Indian actor best known for his versatile and intense performances in Tamil-language films.
  • C. Vikram
    Vikram is the lunar lander of India’s Chandrayaan-3 mission, designed to achieve a soft landing on the Moon’s surface.
  • D. Pavanputra
    Pavanputra is a revered epithet of the Hindu deity Hanuman, highlighting his divine parentage as the son of the wind god.
  • E. Shanmukha
    Shanmukha is a revered Hindu deity of war and victory, widely worshipped as the six-faced son of Shiva and Parvati.
  • 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: Harsha
Triple: [Ancient India, notableRuler, Harsha]
Generated description
Harsha was a 7th-century Indian emperor who unified much of northern India and became renowned for his patronage of Buddhism, literature, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Harsha
Target entity description: Harsha was a 7th-century Indian emperor who unified much of northern India and became renowned for his patronage of Buddhism, literature, and the arts.
  • A. Harish
    Harish is the given name of Harish-Chandra, a prominent Indian-American mathematician and physicist known for his foundational work in representation theory.
  • B. Vikram
    Vikram is a prominent Indian actor best known for his versatile and intense performances in Tamil-language films.
  • C. Vikram
    Vikram is the lunar lander of India’s Chandrayaan-3 mission, designed to achieve a soft landing on the Moon’s surface.
  • D. Pavanputra
    Pavanputra is a revered epithet of the Hindu deity Hanuman, highlighting his divine parentage as the son of the wind god.
  • E. Shanmukha
    Shanmukha is a revered Hindu deity of war and victory, widely worshipped as the six-faced son of Shiva and Parvati.
  • 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_69bd43d6251c81909deecce3e6e9d69c completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd571412788190a374abd1e05519e4 completed March 20, 2026, 2:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd7f8b19ac819099e9249d31660f52 completed March 20, 2026, 5:10 p.m.
NEDg Description generation batch_69bd84bae7148190ae201ea5257dd43e completed March 20, 2026, 5:32 p.m.
NED2 Entity disambiguation (via description) batch_69bd857181e4819086b7d0b493fbb9a3 completed March 20, 2026, 5:35 p.m.
Created at: March 20, 2026, 1:01 p.m.