Triple

T8667420
Position Surface form Disambiguated ID Type / Status
Subject Sivaji Ganesan E205710 entity
Predicate child P120 FINISHED
Object Prabhu
Prabhu is an Indian film actor best known for his work in Tamil cinema and as the son of legendary actor Sivaji Ganesan.
E749956 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: Prabhu | Statement: [Sivaji Ganesan, child, Prabhu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prabhu
Context triple: [Sivaji Ganesan, child, Prabhu]
  • A. Prabhasa
    Prabhasa is a sacred coastal pilgrimage site in western India, traditionally associated with the Yadava clan and the end of Lord Krishna’s earthly life.
  • B. Simhadri
    Simhadri is a 2003 Telugu-language action drama film starring Jr. NTR that became one of director S. S. Rajamouli’s early commercial blockbusters.
  • C. Shabara Svamin
    Shabara Svamin was an influential early Indian philosopher and commentator whose work on the Mimamsa school’s foundational texts significantly shaped Hindu ritual and hermeneutic thought.
  • D. Prabaker
    Prabaker is a cheerful and loyal Indian guide and friend who plays a central supporting role in Gregory David Roberts' novel "Shantaram."
  • E. Raghava
    Raghava is an epithet of the Hindu deity Rama, highlighting his lineage from the Raghu dynasty and his role as a central hero of the Ramayana.
  • 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: Prabhu
Triple: [Sivaji Ganesan, child, Prabhu]
Generated description
Prabhu is an Indian film actor best known for his work in Tamil cinema and as the son of legendary actor Sivaji Ganesan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Prabhu
Target entity description: Prabhu is an Indian film actor best known for his work in Tamil cinema and as the son of legendary actor Sivaji Ganesan.
  • A. Prabhasa
    Prabhasa is a sacred coastal pilgrimage site in western India, traditionally associated with the Yadava clan and the end of Lord Krishna’s earthly life.
  • B. Simhadri
    Simhadri is a 2003 Telugu-language action drama film starring Jr. NTR that became one of director S. S. Rajamouli’s early commercial blockbusters.
  • C. Shabara Svamin
    Shabara Svamin was an influential early Indian philosopher and commentator whose work on the Mimamsa school’s foundational texts significantly shaped Hindu ritual and hermeneutic thought.
  • D. Prabaker
    Prabaker is a cheerful and loyal Indian guide and friend who plays a central supporting role in Gregory David Roberts' novel "Shantaram."
  • E. Raghava
    Raghava is an epithet of the Hindu deity Rama, highlighting his lineage from the Raghu dynasty and his role as a central hero of the Ramayana.
  • 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_69ca83516ae88190aefe034b3bc589e3 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc48a34b808190aa9aed9cdb2900e6 completed March 31, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69cecd1ca88c8190a3b2ca79a7204248 completed April 2, 2026, 8:10 p.m.
NEDg Description generation batch_69cece8fcbcc8190832a66287bc8f833 completed April 2, 2026, 8:16 p.m.
NED2 Entity disambiguation (via description) batch_69cecff48600819086a15700cb947056 completed April 2, 2026, 8:22 p.m.
Created at: March 30, 2026, 6:31 p.m.