Triple

T8541821
Position Surface form Disambiguated ID Type / Status
Subject Pastaza Kichwa E202214 entity
Predicate relatedGroup P37 FINISHED
Object Tena Kichwa
Tena Kichwa is a variety of Amazonian Kichwa spoken around the town of Tena in Ecuador, closely associated with the Indigenous Kichwa communities of that region.
E741173 NE FINISHED

How this triple was built (4 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: Tena Kichwa | Statement: [Pastaza Kichwa, relatedGroup, Tena Kichwa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tena Kichwa
Context triple: [Pastaza Kichwa, relatedGroup, Tena Kichwa]
  • A. Gambiri Kati
    Gambiri Kati is an alternative name for the Tregami language, an Indo-Iranian language spoken in parts of eastern Afghanistan.
  • B. M’kira
    M’kira is a small town and commune located in Tizi Ouzou Province in northern Algeria, within the Kabylie region.
  • C. Matsigenka
    The Matsigenka are an Indigenous people of the Peruvian Amazon known for their forest-based subsistence lifestyle, distinct language, and rich shamanic and cosmological traditions.
  • D. Maanami Mamani
    Maanami Mamani is a writer best known for contributing to the work "Through the Wire."
  • E. Mandura Gumuz
    Mandura Gumuz is a Gumuz language spoken by the Gumuz people of western Ethiopia.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tena Kichwa
Triple: [Pastaza Kichwa, relatedGroup, Tena Kichwa]
Generated description
Tena Kichwa is a variety of Amazonian Kichwa spoken around the town of Tena in Ecuador, closely associated with the Indigenous Kichwa communities of that region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tena Kichwa
Target entity description: Tena Kichwa is a variety of Amazonian Kichwa spoken around the town of Tena in Ecuador, closely associated with the Indigenous Kichwa communities of that region.
  • A. Gambiri Kati
    Gambiri Kati is an alternative name for the Tregami language, an Indo-Iranian language spoken in parts of eastern Afghanistan.
  • B. M’kira
    M’kira is a small town and commune located in Tizi Ouzou Province in northern Algeria, within the Kabylie region.
  • C. Matsigenka
    The Matsigenka are an Indigenous people of the Peruvian Amazon known for their forest-based subsistence lifestyle, distinct language, and rich shamanic and cosmological traditions.
  • D. Maanami Mamani
    Maanami Mamani is a writer best known for contributing to the work "Through the Wire."
  • E. Mandura Gumuz
    Mandura Gumuz is a Gumuz language spoken by the Gumuz people of western Ethiopia.
  • F. None of above. chosen

Provenance (5 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_69ca832461e88190a654c5e44e233aa8 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe6e10bc081909a7210c577b807fb completed March 31, 2026, 3:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce6da3d65c819087ed6b46dfc35885 completed April 2, 2026, 1:22 p.m.
NEDg Description generation batch_69ce6ec3b080819082d64646d453541d completed April 2, 2026, 1:27 p.m.
NED2 Entity disambiguation (via description) batch_69ce6fe928d48190824e7a94fea5cfc0 completed April 2, 2026, 1:32 p.m.
Created at: March 30, 2026, 6:18 p.m.