Triple

T12968400
Position Surface form Disambiguated ID Type / Status
Subject Johannes Agricola E321328 entity
Predicate familyName P18 FINISHED
Object Agricola E93656 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: Agricola | Statement: [Johannes Agricola, familyName, Agricola]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Agricola
Context triple: [Johannes Agricola, familyName, Agricola]
  • A. Agricola chosen
    Agricola is a Finnish surname most famously borne by Mikael Agricola, the 16th-century clergyman known as the father of written Finnish.
  • B. Agricola
    Agricola is a biographical and historical work by the Roman historian Tacitus that recounts the life and military career of his father-in-law, the general Gnaeus Julius Agricola, and reflects on Roman rule in Britain.
  • C. Agricola Tower
    Agricola Tower is a historic medieval tower that forms part of the Chester Castle complex in Chester, England.
  • D. Splendor
    Splendor is the English rendering of the Hebrew word "Zohar," the title of the central mystical text of Kabbalah in Jewish tradition.
  • E. Citadels
    Citadels is a popular strategic card game known for its role selection, bluffing, and city-building mechanics.
  • 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_69d80763bd6c819094437da5b20b01d2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e407e5081909424fc0c22483c28 completed April 10, 2026, 10:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8e6b31c8190b09276003f284f25 completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 8:32 p.m.