Triple

T4721471
Position Surface form Disambiguated ID Type / Status
Subject Lake Maggiore E104775 entity
Predicate hasCityOnShore P969 FINISHED
Object Verbania E178417 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: Verbania | Statement: [Lake Maggiore, hasCityOnShore, Verbania]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Verbania
Context triple: [Lake Maggiore, hasCityOnShore, Verbania]
  • A. Verbania chosen
    Verbania is a lakeside city in northern Italy, situated on the shores of Lake Maggiore near the Swiss border.
  • B. Banavasi
    Banavasi is an ancient town in Karnataka, India, historically significant as an early capital of the Kadamba dynasty and a major center of early Kannada culture and inscriptions.
  • C. Kalka
    Kalka is a town in the Indian state of Haryana, known as a gateway to the Himalayan hill stations and the starting point of the Kalka–Shimla railway.
  • D. Tathra
    Tathra is a coastal town on the Sapphire Coast of New South Wales, Australia, known for its historic wharf, scenic beaches, and fishing.
  • E. Sabni
    Sabni was an ancient Egyptian official from the Old Kingdom whose rock-cut tomb at Aswan’s Tombs of the Nobles is notable for its detailed inscriptions and scenes illustrating his life and status.
  • 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_69bd43ec4a348190bc41afae43375e71 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd642a1a808190afeefc9d65e6c539 completed March 20, 2026, 3:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69be1094fd9c81909e12723394f9ae0a completed March 21, 2026, 3:29 a.m.
Created at: March 20, 2026, 1:18 p.m.