Triple
T16083830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colocolo |
E390177
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Mapudungun |
E234600
|
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: Mapudungun | Statement: [Colocolo, language, Mapudungun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mapudungun Context triple: [Colocolo, language, Mapudungun]
-
A.
Mapudungun
chosen
Mapudungun is an indigenous language of South America spoken primarily by the Mapuche people in Chile and Argentina.
-
B.
Puel Mapu
Puel Mapu is the eastern portion of the ancestral Mapuche territory, located mainly in what is now Argentina.
-
C.
Mazabuka
Mazabuka is a town in southern Zambia known for its sugar industry and agricultural production.
-
D.
Mabasa
Mabasa is a barangay (village-level administrative division) within the municipality of Argao in Cebu, Philippines.
-
E.
Mapusa
Mapusa is a bustling commercial town in North Goa, India, known as a major market and transport hub near the popular beaches of the state.
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1844d7d688190b5badac7a8014f89 |
completed | April 17, 2026, 12:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe48cf76c8190bc96168fc2326ffb |
completed | May 10, 2026, 1:51 a.m. |
Created at: April 10, 2026, 4:59 a.m.