Triple

T15871123
Position Surface form Disambiguated ID Type / Status
Subject Rambu Tuka' E384831 entity
Predicate religiousContext P45 FINISHED
Object Aluk To Dolo E384828 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: Aluk To Dolo | Statement: [Rambu Tuka', religiousContext, Aluk To Dolo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aluk To Dolo
Context triple: [Rambu Tuka', religiousContext, Aluk To Dolo]
  • A. Aluk To Dolo chosen
    Aluk To Dolo is the traditional animist belief system of the Toraja people of Indonesia, centered on elaborate ancestor worship and complex funeral rituals.
  • B. Alukuyana
    Alukuyana is an alternative name for the Wayana language, an indigenous Cariban language spoken in parts of Brazil, Suriname, and French Guiana.
  • C. Alutus
    Alutus is the ancient name of the Olt River, a major waterway flowing through central Romania into the Danube.
  • D. Aluta
    Aluta is the historical name of the Olt River, a major waterway flowing through central Romania.
  • E. Auzaar
    Auzaar is a 1997 Bollywood action thriller film directed by Sohail Khan, starring Salman Khan and Sanjay Kapoor.
  • 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e155fa1aac81908e4b86abedf295ca completed April 16, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb59ddc488190ae6b6913f85005f6 completed May 9, 2026, 10:30 p.m.
Created at: April 10, 2026, 4:50 a.m.