Triple

T5024554
Position Surface form Disambiguated ID Type / Status
Subject Vibhishana E112941 entity
Predicate opposedTo P437 FINISHED
Object Ravana E112600 NE FINISHED

How this triple was built (2 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: Ravana | Statement: [Vibhishana, opposedTo, Ravana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ravana
Context triple: [Vibhishana, opposedTo, Ravana]
  • A. Ravana chosen
    Ravana is the ten-headed demon king of Lanka in Hindu mythology, best known as the powerful antagonist of the epic Ramayana.
  • B. Andhaka
    Andhaka is a prominent clan within the ancient Yadava lineage of Hindu tradition, often associated with the family and kingdom of Krishna.
  • C. Mahishasura
    Mahishasura is a powerful buffalo demon in Hindu mythology, best known as the formidable adversary slain by the goddess Durga in a legendary cosmic battle.
  • D. Vibhishana
    Vibhishana is a virtuous rakshasa prince in the Hindu epic Ramayana, known for abandoning his brother Ravana to ally with Rama and uphold dharma.
  • E. Hiranyakashipu
    Hiranyakashipu is a powerful demon king from Hindu mythology, best known as the tyrannical father of Prahlada and the antagonist slain by Vishnu’s Narasimha avatar.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd4435c2f48190be593158cbfcf8a3 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd736852e88190b69d6561ca7604c3 completed March 20, 2026, 4:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69bed90afc5c8190b205341d1e9dc7bc completed March 21, 2026, 5:44 p.m.
Created at: March 20, 2026, 1:36 p.m.