Triple
T6731227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Oceanic languages |
E153637
|
entity |
| Predicate | includesLanguage |
P2177
|
FINISHED |
| Object | Drehu |
E199536
|
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: Drehu | Statement: [Southern Oceanic languages, includesLanguage, Drehu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drehu Context triple: [Southern Oceanic languages, includesLanguage, Drehu]
-
A.
Drehu
chosen
Drehu is an Austronesian language spoken primarily by the indigenous population of Lifou Island in New Caledonia.
-
B.
Dhordo
Dhordo is a village in Gujarat, India, renowned as a gateway to the White Rann of Kutch and a popular desert tourism destination.
-
C.
Gouderak
Gouderak is a small village in the Dutch province of South Holland, situated along the Hollandse IJssel river.
-
D.
Rába
Rába is a river in Central Europe that flows primarily through western Hungary and parts of Austria, eventually joining the Danube.
-
E.
Dolgan
Dolgan is a Turkic language spoken primarily by the Dolgan people in northern Siberia, especially in Russia’s Taymyr Peninsula.
- 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_69c6880bdd68819097de8b6099992682 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d16a30888190ae474d90bb71ac49 |
completed | March 27, 2026, 6:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c70b029960819090de37c99e80ceb9 |
completed | March 27, 2026, 10:56 p.m. |
Created at: March 27, 2026, 2:09 p.m.