Triple

T17750718
Position Surface form Disambiguated ID Type / Status
Subject Sissu E443103 entity
Predicate roadConnection P385 FINISHED
Object Keylong 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: Keylong | Statement: [Sissu, roadConnection, Keylong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keylong
Context triple: [Sissu, roadConnection, Keylong]
  • A. Keylong chosen
    Keylong is a small town in the Indian state of Himachal Pradesh, known as the main urban center of the remote Lahaul region in the Himalayas.
  • B. Kettenis
    Kettenis is a village and municipal section of the city of Eupen in the German-speaking Community of eastern Belgium.
  • C. Master Kau
    Master Kau is the stern yet comically superstitious Taoist priest and vampire hunter who serves as the central protagonist in the Hong Kong horror-comedy film "Mr. Vampire."
  • D. Knightro
    Knightro is the costumed knight mascot representing the University of Central Florida at its athletic events and campus activities.
  • E. Kengamine
    Kengamine is the main summit of Mount Norikura, a prominent volcanic peak in Japan’s Northern Alps.
  • 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4841a401c8190ae1dc0ed7ae4cc26 completed April 19, 2026, 7:28 a.m.
Created at: April 10, 2026, 10:10 a.m.