Triple

T4188742
Position Surface form Disambiguated ID Type / Status
Subject Mangal Pandey E88380 entity
Predicate givenName P17 FINISHED
Object Mangal E88380 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: Mangal | Statement: [Mangal Pandey, givenName, Mangal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mangal
Context triple: [Mangal Pandey, givenName, Mangal]
  • A. Mangal chosen
    Mangal is a given name most notably borne by Mangal Pandey, an Indian soldier whose actions helped spark the Indian Rebellion of 1857.
  • B. Varuna
    Varuna is a large, rapidly rotating trans-Neptunian object in the Kuiper Belt, notable for its elongated shape and classification as a likely dwarf-planet candidate.
  • C. Varuna
    Varuna is an ancient Vedic god primarily associated with cosmic order, moral law, and the waters, often regarded as a sovereign guardian of ṛta (universal order).
  • D. Chand
    Chand is a common South Asian given name and surname derived from the Sanskrit word for "moon," often used across India and neighboring regions.
  • E. Saha
    Saha is a surname most notably associated with Indian astrophysicist Meghnad Saha, known for the Saha ionization equation in stellar astrophysics.
  • 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_69aed9477e8c81908bcb862d2db55b1d completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af0326eaec819083cd298c9219dd15 completed March 9, 2026, 5:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69b58a034f6481909a3126d8832f7821 completed March 14, 2026, 4:17 p.m.
Created at: March 9, 2026, 3:46 p.m.