Triple

T447649
Position Surface form Disambiguated ID Type / Status
Subject Maratha Empire E7055 entity
Predicate administrativeCenter P1474 FINISHED
Object Pune E14838 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: Pune | Statement: [Maratha Empire, administrativeCenter, Pune]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pune
Context triple: [Maratha Empire, administrativeCenter, Pune]
  • A. Pune chosen
    Pune is a major cultural, educational, and IT hub in the western Indian state of Maharashtra, known for its universities, historical significance, and rapidly growing urban economy.
  • B. Nagpur
    Nagpur is a major city in the Indian state of Maharashtra, known as a key political and commercial center and often referred to as the "Orange City" for its famous orange production.
  • C. Nashik
    Nashik is a historic city in the Indian state of Maharashtra, known for its religious significance in Hinduism and as a major center of wine production.
  • D. Nanded
    Nanded is a historic city in the Indian state of Maharashtra, known as an important Sikh pilgrimage center and a major urban hub in the Marathwada region.
  • E. Mumbai
    Mumbai is a densely populated coastal metropolis in western India that serves as the country’s financial hub and the center of its film industry, Bollywood.
  • 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_69a2e7e4676c81909ea0dbdecac0687c completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ef6429e881908aa758da64299a16 completed Feb. 28, 2026, 1:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4e3f1e5908190850594ccb37f364a completed March 2, 2026, 1:12 a.m.
Created at: Feb. 28, 2026, 1:12 p.m.