Triple

T14975705
Position Surface form Disambiguated ID Type / Status
Subject Parbat District E373440 entity
Predicate capital P234 FINISHED
Object Kusma E701218 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: Kusma | Statement: [Parbat District, capital, Kusma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kusma
Context triple: [Parbat District, capital, Kusma]
  • A. Kushma chosen
    Kushma is a small town in central Nepal known for its dramatic suspension bridges and role as the administrative center of Parbat District.
  • B. Kuzma
    Kuzma is a masculine given name of Slavic origin, historically borne by notable figures such as the Russian national hero Kuzma Minin.
  • C. Vasishka
    Vasishka was a Kushan emperor who ruled parts of northern India and Central Asia in the early 3rd century CE, known primarily from his inscriptions and coinage.
  • D. Kushnar
    Kushnar is an alternative written form or spelling variant of the name Kushner.
  • E. Yunaska
    Yunaska is the maiden surname of Lara Trump, who is married to Eric Trump, son of former U.S. President Donald Trump.
  • 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_69d85ccbbcd48190acb56e7cf104d8ad completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6e8733081908e06b53746eb6eb6 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9692e4fc8190a1194a41fc8a832c completed May 9, 2026, 2:06 a.m.
Created at: April 10, 2026, 2:51 a.m.