Triple

T13630906
Position Surface form Disambiguated ID Type / Status
Subject Colla E325714 entity
Predicate historicallyInhabited P3032 FINISHED
Object Collasuyu E64167 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: Collasuyu | Statement: [Colla, historicallyInhabited, Collasuyu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Collasuyu
Context triple: [Colla, historicallyInhabited, Collasuyu]
  • A. Collasuyu chosen
    Collasuyu was the southeastern quarter of the Inca Empire, encompassing the highland and lowland regions around Lake Titicaca and extending into parts of present-day Bolivia, Chile, and Argentina.
  • B. Cuntisuyu
    Cuntisuyu was one of the four main administrative and territorial divisions of the Inca Empire, located to the southwest of Cusco.
  • C. Chinchaysuyu
    Chinchaysuyu was the northwestern quarter of the Inca Empire, encompassing coastal and highland regions that are now parts of Peru, Ecuador, and Colombia.
  • D. Vilcabamba
    Vilcabamba was the remote Andean stronghold that served as the last refuge of the Inca resistance against Spanish conquest.
  • E. Vilcabamba
    Vilcabamba is a small town in southern Ecuador’s Loja Province, known for its scenic Andean valley setting and reputation for residents’ longevity.
  • 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_69d8076beddc8190a53156f5bea77f5e completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbbe9ea9088190a17270dec82bbcaa completed April 12, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78aeb591481909d39675a543a8b51 completed May 3, 2026, 5:50 p.m.
Created at: April 9, 2026, 9:51 p.m.