Triple

T15204663
Position Surface form Disambiguated ID Type / Status
Subject Skírnismál E363357 entity
Predicate relatedWork P37 FINISHED
Object Lokasenna E359855 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: Lokasenna | Statement: [Skírnismál, relatedWork, Lokasenna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lokasenna
Context triple: [Skírnismál, relatedWork, Lokasenna]
  • A. Lokasenna chosen
    Lokasenna is an Old Norse mythological poem in which the trickster god Loki insults and exposes the secrets of the other gods during a feast.
  • B. Loksado
    Loksado is a rural highland area in South Kalimantan, Indonesia, known for its traditional Dayak culture, rainforest scenery, and bamboo rafting along clear mountain rivers.
  • C. Mandonio
    Mandonio was an Iberian chieftain who led resistance against Roman expansion during the conquest of the Iberian Peninsula.
  • D. Kulisusu
    Kulisusu is a town and administrative center located in the province of Southeast Sulawesi, Indonesia.
  • E. Lakon
    Lakon is an Oceanic language spoken on the island of Gaua in northern Vanuatu.
  • 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e006b7964c8190bc8dc3444b94f15e completed April 15, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69fed33b911c8190815341a342a8d3c8 completed May 9, 2026, 6:24 a.m.
Created at: April 10, 2026, 3:11 a.m.