Triple

T10817004
Position Surface form Disambiguated ID Type / Status
Subject Uttara Kannada district E255256 entity
Predicate hasTown P847 FINISHED
Object Kumta E555170 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: Kumta | Statement: [Uttara Kannada district, hasTown, Kumta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kumta
Context triple: [Uttara Kannada district, hasTown, Kumta]
  • A. Kumta chosen
    Kumta is a coastal town in Karnataka, India, known for its beaches, temples, and proximity to the Western Ghats.
  • B. Kumher
    Kumher is a historic town in the Braj region of northern India, known for its cultural and religious significance linked to the legends of Lord Krishna.
  • C. Khadakwasla
    Khadakwasla is a suburban area near Pune in Maharashtra, India, known for its lake, dam, and military establishments.
  • D. Kadamtala
    Kadamtala is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
  • E. Kumhrar
    Kumhrar is an archaeological site in Patna, India, known for the excavated remains of ancient Pataliputra, the capital of the Mauryan Empire.
  • 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_69d6aa8081448190a9324184f2bd1c26 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d733eea03c8190a68f4d4f89f497a2 completed April 9, 2026, 5:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69de855799748190b51745a198daa8d0 completed April 14, 2026, 6:20 p.m.
Created at: April 8, 2026, 9:18 p.m.