Triple

T4782397
Position Surface form Disambiguated ID Type / Status
Subject Ramcharitmanas E106396 entity
Predicate mainCharacter P1183 FINISHED
Object Hanuman E21412 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: Hanuman | Statement: [Ramcharitmanas, mainCharacter, Hanuman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hanuman
Context triple: [Ramcharitmanas, mainCharacter, Hanuman]
  • A. Hanuman chosen
    Hanuman is a revered Hindu deity known for his immense strength, unwavering devotion to Lord Rama, and central role in the epic Ramayana.
  • B. Hanuman Pol
    Hanuman Pol is one of the main historic entrance gates of Rajasthan’s Kumbhalgarh Fort, serving as a fortified access point and defensive structure.
  • C. Rama
    Rama is a major Hindu deity and the virtuous prince-king of Ayodhya, revered as the seventh avatar of Vishnu and hero of the epic Ramayana.
  • D. Rama
    Rama is a small scenic village in Pakistan’s Gilgit-Baltistan region, known as a gateway to the lush Rama Meadows and views of Nanga Parbat.
  • E. Narasimha
    Narasimha is the fierce man-lion incarnation of the Hindu god Vishnu, known for destroying the demon king Hiranyakashipu to protect his devotee Prahlada.
  • 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_69bd43f4a9588190bf73e20bc27c03cc completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd65abd0a08190937102c44d102f12 completed March 20, 2026, 3:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69be5c9b1a348190809c1af686b7101a completed March 21, 2026, 8:53 a.m.
Created at: March 20, 2026, 1:22 p.m.