Triple

T19963010
Position Surface form Disambiguated ID Type / Status
Subject Ikshvaku dynasty E479861 entity
Predicate hasNotableKing P25268 FINISHED
Object Sagara 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: Sagara | Statement: [Ikshvaku dynasty, hasNotableKing, Sagara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sagara
Context triple: [Ikshvaku dynasty, hasNotableKing, Sagara]
  • A. Sagara
    Sagara is a town in the Shivamogga district of Karnataka, India, known for its proximity to Jog Falls and the Western Ghats.
  • B. Sagara chosen
    Sagara is a legendary king in Hindu mythology, renowned as an ancestor of Lord Rama and for his role in the origins of the sacred Ganges River’s descent to earth.
  • C. Ariake
    Ariake is a waterfront district in Tokyo known for its large exhibition centers, sports venues, and modern urban development on the artificial islands of Tokyo Bay.
  • D. Akashi
    Akashi was a Japanese warship that served in the Imperial Japanese Navy around the time of the Russo-Japanese War.
  • E. Akashi
    Akashi is a coastal city in western Japan known for its historic castle, views of the Akashi Kaikyō Strait, and its specialty dish akashiyaki.
  • 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65af619108190825cbcfb6b8e1fa5 completed April 20, 2026, 4:57 p.m.
Created at: April 10, 2026, 1:54 p.m.