Triple
T791457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jarawa |
E16922
|
entity |
| Predicate | relatedGroup |
P37
|
FINISHED |
| Object | Great Andamanese (geographical neighbors, not closely related linguistically) |
E16735
|
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: Great Andamanese (geographical neighbors, not closely related linguistically) | Statement: [Jarawa, relatedGroup, Great Andamanese (geographical neighbors, not closely related linguistically)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Great Andamanese (geographical neighbors, not closely related linguistically) Context triple: [Jarawa, relatedGroup, Great Andamanese (geographical neighbors, not closely related linguistically)]
-
A.
Great Andamanese languages
The Great Andamanese languages are a small, nearly extinct group of indigenous languages once spoken by the Great Andamanese peoples of the Andaman Islands in the Bay of Bengal.
-
B.
Great Andamanese
chosen
The Great Andamanese are one of the indigenous peoples of the Andaman Islands, known as a small, endangered community with distinct languages and cultural traditions.
-
C.
Nicobarese
Nicobarese is an Austroasiatic language (or group of related languages) traditionally spoken by the indigenous Nicobarese people of India’s Nicobar Islands.
-
D.
Nicobarese languages
The Nicobarese languages are a group of Austroasiatic languages spoken by the indigenous Nicobarese people of India’s Nicobar Islands in the eastern Indian Ocean.
-
E.
Polynesian outliers
Polynesian outliers are small, culturally Polynesian communities located on islands outside the main Polynesian Triangle, primarily in Melanesia and Micronesia.
- 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_69a4936cb7448190914f5fe4b8d81607 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a798c7608190b9c79c52a1fe0859 |
completed | March 1, 2026, 8:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a67880f9608190b0676eb47ea99ca1 |
completed | March 3, 2026, 5:58 a.m. |
Created at: March 1, 2026, 7:38 p.m.