Triple
T20299811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harakmbut |
E505447
|
entity |
| Predicate | hasLanguage |
P15
|
FINISHED |
| Object | Pukirieri language |
E1421640
|
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: Pukirieri language | Statement: [Harakmbut, hasLanguage, Pukirieri language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pukirieri language Context triple: [Harakmbut, hasLanguage, Pukirieri language]
-
A.
Pucikwar language
Pucikwar language is an endangered indigenous language of the Pucikwar people of the Andaman Islands in India.
-
B.
Paunaka language
The Paunaka language is an endangered Arawakan language traditionally spoken by the Paunaka people of eastern Bolivia.
-
C.
Amarakaeri language
chosen
The Amarakaeri language is an indigenous Harakmbut language spoken by the Amarakaeri people of the Peruvian Amazon.
-
D.
Paraujano language
The Paraujano language is an indigenous Arawakan (Maipurean) language historically spoken by the Paraujano people of northwestern Venezuela, now critically endangered or nearly extinct.
-
E.
Teiwa language
Teiwa language is a Papuan language spoken by the Teiwa people on Pantar Island in eastern Indonesia.
- 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_69e0b4b8ab648190906e18538c250148 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6770b9484819090ffcb339f2a435a |
completed | April 20, 2026, 6:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08611762e481909ee2f41434c86aa5 |
completed | May 16, 2026, 12:20 p.m. |
Created at: April 16, 2026, 11:16 a.m.