Triple
T9080229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | D'Entrecasteaux Islands |
E217599
|
entity |
| Predicate | hasLanguage |
P15
|
FINISHED |
| Object | Dobu language |
E439607
|
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: Dobu language | Statement: [D'Entrecasteaux Islands, hasLanguage, Dobu language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dobu language Context triple: [D'Entrecasteaux Islands, hasLanguage, Dobu language]
-
A.
Dobu language
chosen
Dobu language is an Austronesian language of the Papuan Tip region of Papua New Guinea, traditionally spoken by the Dobu people and used as a local lingua franca.
-
B.
Dobbi language
The Dobbi language is an Ethiopian Semitic language spoken by the Gurage people as part of the broader Gurage language group.
-
C.
Logba language
The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
-
D.
Uduk language
The Uduk language is a Nilo-Saharan language spoken primarily by the Uduk people of eastern Sudan and western Ethiopia.
-
E.
Tubatulabal language
The Tubatulabal language is an endangered Uto-Aztecan language traditionally spoken by the Tubatulabal people of the southern Sierra Nevada region in California.
- 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_69ca83d7a0388190ba1af89ed7ba36f9 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc9607942c8190a21620892ce3cbe5 |
completed | April 1, 2026, 3:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cffe2103448190bbc09436f19c4f11 |
completed | April 3, 2026, 5:51 p.m. |
Created at: March 30, 2026, 7:13 p.m.