Triple

T19978849
Position Surface form Disambiguated ID Type / Status
Subject Gutar E493761 entity
Predicate historicalDocument P55104 FINISHED
Object Gutasaga 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: Gutasaga | Statement: [Gutar, historicalDocument, Gutasaga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gutasaga
Context triple: [Gutar, historicalDocument, Gutasaga]
  • A. Gutasaga chosen
    Gutasaga is a medieval Old Gutnish saga that recounts the legendary origins, history, and laws of the people of Gotland.
  • B. Ságat
    Ságat is a Norwegian Sámi-language newspaper that serves as a key regional news source for the Sámi people.
  • C. Gudriolum
    Gudriolum is a Turkmenistani city located along the border with Iran, serving as a local hub for cross-border interaction and trade.
  • D. Edda
    Edda is an Italian given name most notably borne by Edda Mussolini, the eldest daughter of dictator Benito Mussolini.
  • E. Oddusuddan
    Oddusuddan is a town in Sri Lanka’s Northern Province that gained prominence due to its strategic location and role in the country’s civil conflict.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d11108481908241a2a96a795a7d completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:27 p.m.