Triple

T5344014
Position Surface form Disambiguated ID Type / Status
Subject Huari culture E124007 entity
Predicate hadMajorSite P2462 FINISHED
Object Pikillaqta E239697 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: Pikillaqta | Statement: [Huari culture, hadMajorSite, Pikillaqta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pikillaqta
Context triple: [Huari culture, hadMajorSite, Pikillaqta]
  • A. Pikillaqta chosen
    Pikillaqta is a large pre-Inca archaeological complex in Peru known for its planned urban layout and association with the Wari civilization.
  • B. Pichasca
    Pichasca is a small settlement in Chile known for its proximity to the Hurtado River and the surrounding Andean landscapes.
  • C. Pichillaima
    Pichillaima is a summit crater located at the top of Chile’s active Llaima Volcano in the Andes.
  • D. Pitalito
    Pitalito is a major town and coffee-producing hub in southern Colombia, known as one of the country’s most important centers for high-quality coffee.
  • E. Yumbel
    Yumbel is a small Chilean city known for its religious festivities and agricultural surroundings in the Biobío Region.
  • 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_69bd464be27081908807b40b75c1bbae completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd91aab9348190a373b30bb305f933 completed March 20, 2026, 6:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf21c5f82481908e9061d68c1e7496 completed March 21, 2026, 10:55 p.m.
Created at: March 20, 2026, 2:01 p.m.