Triple

T12801202
Position Surface form Disambiguated ID Type / Status
Subject Summajärvi E306020 entity
Predicate nearbySettlement P350 FINISHED
Object Summa E1002929 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: Summa | Statement: [Summajärvi, nearbySettlement, Summa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Summa
Context triple: [Summajärvi, nearbySettlement, Summa]
  • A. Summa
    Summa is a comprehensive, systematically organized theological treatise characteristic of medieval scholastic thought, exemplified by works like Thomas Aquinas’s Summa Theologiae.
  • B. Summa chosen
    Summa is a locality in Finland best known as a major battlefield of the Winter War between Finland and the Soviet Union.
  • C. Suum Cuique
    Suum Cuique is a Latin phrase meaning "to each his own," historically used as a motto expressing the principle of giving every person their due.
  • D. Summvs
    Summvs is a collaborative experimental electronic album by Alva Noto and Ryuichi Sakamoto, known for its minimalist piano and glitch-based soundscapes.
  • E. Summus Poeninus
    Summus Poeninus is the Latin name for the Great St Bernard Pass, a historic Alpine route linking Switzerland and Italy that has served as a key transalpine crossing since antiquity.
  • 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_69d7bdf366888190a8cccb982606889c completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e7d3f5c8190bf01bef5d263ca26 completed April 10, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68ec0d5dc819099a8036c6cbac634 completed May 2, 2026, 11:54 p.m.
Created at: April 9, 2026, 5:30 p.m.