Triple
T6663362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ambrym |
E151530
|
entity |
| Predicate | hasLanguage |
P15
|
FINISHED |
| Object | Daakie language |
E608747
|
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: Daakie language | Statement: [Ambrym, hasLanguage, Daakie language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daakie language Context triple: [Ambrym, hasLanguage, Daakie language]
-
A.
Daakaka language
chosen
The Daakaka language is an Oceanic language spoken by communities on Ambrym Island in Vanuatu.
-
B.
Jangil language
The Jangil language is an extinct and poorly documented Ongan language once spoken by the Jangil (Rutland Island) people of the Andaman Islands in India.
-
C.
Modang language
The Modang language is an Austronesian language spoken by the Modang people of Borneo, primarily in East Kalimantan, Indonesia.
-
D.
Kaado language
The Kaado language is a regional variety within the Songhay language family spoken by communities in parts of West Africa.
-
E.
Amdang language
The Amdang language is an Eastern Sudanic language spoken primarily in eastern Chad and western Sudan, closely associated with the Fur people and region.
- 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_69c687f5fac48190a09e4838d9c6b45d |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6b09a6fa88190ba8e454b9ad421a0 |
completed | March 27, 2026, 4:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6f79cf0e48190a69294f3b13a8372 |
completed | March 27, 2026, 9:33 p.m. |
Created at: March 27, 2026, 2:02 p.m.