Triple

T21531225
Position Surface form Disambiguated ID Type / Status
Subject Mercedonius E531233 entity
Predicate effectOnYearLength P49552 FINISHED
Object extended the Roman year beyond 355 days LITERAL 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: extended the Roman year beyond 355 days | Statement: [Mercedonius, effectOnYearLength, extended the Roman year beyond 355 days]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: effectOnYearLength
Context triple: [Mercedonius, effectOnYearLength, extended the Roman year beyond 355 days]
  • A. hasAverageYearLength
    Indicates that one entity has a specified average duration for its year (orbital period), typically measured over time.
  • B. additionalDaysPerYear chosen
    Indicates the number of extra days added each year to a base or standard duration.
  • C. accuracyComparedToTropicalYear
    Indicates how closely something’s measured or defined duration matches the length of a tropical year.
  • D. earthDayLengthening_rateMillisecondsPerCentury
    Indicates the rate at which the length of an Earth day increases, measured in milliseconds per century.
  • E. driftPerYearRelativeToTropicalYearDays
    Indicates the amount of calendar drift, measured in days per year, relative to the length of the tropical year.
  • F. None of above.

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_69e0c45e5b8881908ac18fc2f493b114 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee9d08ebf881909574e098404f93fa completed April 26, 2026, 11:17 p.m.
PD Predicate disambiguation batch_69e6320043bc81909417c41a718652ba completed April 20, 2026, 2:02 p.m.
Created at: April 16, 2026, 6:27 p.m.