Triple
T16236337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Secoya people |
E394121
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Secoya language |
E743036
|
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: Secoya language | Statement: [Secoya people, language, Secoya language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Secoya language Context triple: [Secoya people, language, Secoya language]
-
A.
Secoya language
chosen
The Secoya language is a Western Tucanoan language spoken by the Secoya people of the Amazonian regions of Ecuador and Peru.
-
B.
Piapoco language
The Piapoco language is an indigenous Arawakan language spoken by the Piapoco people of Colombia and Venezuela.
-
C.
Yucuna language
The Yucuna language is an indigenous Arawakan language spoken by the Yucuna people of the Colombian Amazon.
-
D.
Sipakapense language
The Sipakapense language is a Mayan language spoken by the Sipakapense people in the western highlands of Guatemala.
-
E.
Shipibo-Conibo language
The Shipibo-Conibo language is an indigenous Panoan language of the Peruvian Amazon, spoken primarily by the Shipibo-Conibo people along the Ucayali River.
- 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_69d87f204df88190a8f88923decf9835 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2455abc608190ba3308c15c9e8a23 |
completed | April 17, 2026, 2:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a000ed8cbe48190be68ccade55211ad |
completed | May 10, 2026, 4:51 a.m. |
Created at: April 10, 2026, 5:04 a.m.