Triple

T7045039
Position Surface form Disambiguated ID Type / Status
Subject Hoysalas E163610 entity
Predicate capital P234 FINISHED
Object Halebidu E641465 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: Halebidu | Statement: [Hoysalas, capital, Halebidu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Halebidu
Context triple: [Hoysalas, capital, Halebidu]
  • A. Belur
    Belur is a locality in the Howrah district of West Bengal, India, known for its proximity to the Hooghly River and the famous Belur Math.
  • B. Belur chosen
    Belur is a historic town in Karnataka, India, renowned for its exquisite Hoysala-era temple architecture, especially the Chennakeshava Temple.
  • C. Hampi
    Hampi is an ancient ruined city in Karnataka, India, famed for its monumental Hindu temples and as the former capital of the Vijayanagara Empire.
  • D. Badami
    Badami is a historic town in Karnataka, India, renowned for its rock-cut cave temples and ancient Chalukyan architecture.
  • E. Devanahalli
    Devanahalli is a town near Bengaluru in the Indian state of Karnataka, notable for its rapid development and proximity to Kempegowda International Airport.
  • 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_69c6885f598c8190b6b6495c59d8d962 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e238c7a4819095f5ff7283d48da8 completed March 27, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7a313f0c88190834daf87723a77a1 completed March 28, 2026, 9:44 a.m.
Created at: March 27, 2026, 2:37 p.m.