Triple
T21479331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wik peoples |
E529946
|
entity |
| Predicate | hasLanguage |
P15
|
FINISHED |
| Object |
Wik languages
Wik languages are a group of closely related Australian Aboriginal languages traditionally spoken by the Wik peoples of western Cape York Peninsula in Queensland.
|
E1486026
|
NE FINISHED |
How this triple was built (4 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: Wik languages | Statement: [Wik peoples, hasLanguage, Wik languages]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wik languages Context triple: [Wik peoples, hasLanguage, Wik languages]
-
A.
Wa language
The Wa language is a Mon–Khmer language spoken primarily by the Wa people in parts of Myanmar and China.
-
B.
Li languages
Li languages are a group of closely related Kra–Dai languages spoken primarily by the Li (Hlai) people on China’s Hainan Island.
-
C.
Tiwa languages
The Tiwa languages are a group of closely related Tanoan languages spoken by Tiwa Pueblo peoples in parts of New Mexico and Texas.
-
D.
Willaumez languages
The Willaumez languages are a small subgroup of Western Oceanic Austronesian languages spoken around the Willaumez Peninsula region of New Britain in Papua New Guinea.
-
E.
Jarawan languages
Jarawan languages are a small group of Bantoid (often considered Bantu-related) languages spoken primarily in parts of Nigeria and Cameroon.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Wik languages Triple: [Wik peoples, hasLanguage, Wik languages]
Generated description
Wik languages are a group of closely related Australian Aboriginal languages traditionally spoken by the Wik peoples of western Cape York Peninsula in Queensland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Wik languages Target entity description: Wik languages are a group of closely related Australian Aboriginal languages traditionally spoken by the Wik peoples of western Cape York Peninsula in Queensland.
-
A.
Wa language
The Wa language is a Mon–Khmer language spoken primarily by the Wa people in parts of Myanmar and China.
-
B.
Li languages
Li languages are a group of closely related Kra–Dai languages spoken primarily by the Li (Hlai) people on China’s Hainan Island.
-
C.
Tiwa languages
The Tiwa languages are a group of closely related Tanoan languages spoken by Tiwa Pueblo peoples in parts of New Mexico and Texas.
-
D.
Willaumez languages
The Willaumez languages are a small subgroup of Western Oceanic Austronesian languages spoken around the Willaumez Peninsula region of New Britain in Papua New Guinea.
-
E.
Jarawan languages
Jarawan languages are a small group of Bantoid (often considered Bantu-related) languages spoken primarily in parts of Nigeria and Cameroon.
- F. None of above. chosen
Provenance (5 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea1a37a88190845810cbcacbad65 |
completed | April 23, 2026, 9:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09cfff6dec8190ab480491c4a3f641 |
completed | May 17, 2026, 2:26 p.m. |
| NEDg | Description generation | batch_6a09d0cd3068819094392cc4b7c6d061 |
completed | May 17, 2026, 2:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09d1b4f4748190b5d4edfc298272e4 |
completed | May 17, 2026, 2:33 p.m. |
Created at: April 16, 2026, 6:20 p.m.