Triple

T17951687
Position Surface form Disambiguated ID Type / Status
Subject Prithvi E448845 entity
Predicate familyIncludes P3600 FINISHED
Object Prithvi II NE NERFINISHED

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: Prithvi II | Statement: [Prithvi, familyIncludes, Prithvi II]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prithvi II
Context triple: [Prithvi, familyIncludes, Prithvi II]
  • A. Prithvi I chosen
    Prithvi I is the first variant of India’s Prithvi series of short-range, road-mobile, surface-to-surface ballistic missiles developed under the Integrated Guided Missile Development Program.
  • B. Krishna Vilas
    Krishna Vilas is a historic section of Udaipur’s City Palace complex, known for its royal chambers and traditional Rajasthani architecture.
  • C. Hem Chandra Vikramaditya
    Hem Chandra Vikramaditya, commonly known as Hemu, was a 16th-century Hindu general and king who briefly established himself as a powerful ruler in North India during the Sur and early Mughal period.
  • D. Vikram
    Vikram is the lunar lander of India’s Chandrayaan-3 mission, designed to achieve a soft landing on the Moon’s surface.
  • E. Vikram
    Vikram is a prominent Indian actor best known for his versatile and intense performances in Tamil-language films.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4afac95048190a5d1ef012899c62b completed April 19, 2026, 10:34 a.m.
Created at: April 10, 2026, 10:21 a.m.