Triple

T37047506
Position Surface form Disambiguated ID Type / Status
Subject Kusaasi E916956 entity
Predicate traditionalCalendarEvent P10524 FINISHED
Object harvest festivals 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: harvest festivals | Statement: [Kusaasi, traditionalCalendarEvent, harvest festivals]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: traditionalCalendarEvent
Context triple: [Kusaasi, traditionalCalendarEvent, harvest festivals]
  • A. calendarTradition
    Indicates a relationship where a calendar is based on, follows, or embodies a particular cultural, religious, or historical tradition.
  • B. partOfCalendar
    Indicates that one temporal element (such as an event, date, or period) belongs to, is contained within, or is scheduled as a component of a particular calendar.
  • C. traditionalHoliday chosen
    Indicates that an event or celebration is recognized as a customary or long-established holiday within a culture or community.
  • D. dateEvent
    Indicates that an event takes place or is scheduled on a specific date.
  • E. calendarType
    Indicates the type or system of calendar associated with an entity (e.g., Gregorian, lunar, fiscal).
  • 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_69f76e94d0308190a3f06890e133c88e completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69ffb5c373948190a6606e8caa87a384 completed May 9, 2026, 10:31 p.m.
PD Predicate disambiguation batch_69ffb261da788190b41399df8ed895e8 completed May 9, 2026, 10:17 p.m.
Created at: May 3, 2026, 4:14 p.m.