Triple
T14010323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nupoid languages |
E337060
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object |
Kupa–Dibo cluster
The Kupa–Dibo cluster is a subgroup of closely related Nupoid languages spoken in central Nigeria.
|
E1073892
|
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: Kupa–Dibo cluster | Statement: [Nupoid languages, hasMember, Kupa–Dibo cluster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kupa–Dibo cluster Context triple: [Nupoid languages, hasMember, Kupa–Dibo cluster]
-
A.
Beti-Fang cluster
The Beti-Fang cluster is a group of closely related Bantu languages spoken primarily in Cameroon, Equatorial Guinea, and neighboring Central African regions.
-
B.
Laizo-Falam cluster
The Laizo-Falam cluster is a group of closely related dialects of the Falam Chin language spoken by Chin communities in western Myanmar.
-
C.
Kulisusu–Koroni cluster
The Kulisusu–Koroni cluster is a subgroup of closely related Austronesian languages spoken in southeastern Sulawesi, Indonesia.
-
D.
Berta cluster
Berta cluster is a group of closely related Berta languages spoken primarily in the border regions of Sudan and Ethiopia.
-
E.
Jewel Box cluster
The Jewel Box cluster is a bright and colorful open star cluster in the constellation Crux, renowned for its striking mix of blue and red stars visible even in small telescopes.
- 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: Kupa–Dibo cluster Triple: [Nupoid languages, hasMember, Kupa–Dibo cluster]
Generated description
The Kupa–Dibo cluster is a subgroup of closely related Nupoid languages spoken in central Nigeria.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kupa–Dibo cluster Target entity description: The Kupa–Dibo cluster is a subgroup of closely related Nupoid languages spoken in central Nigeria.
-
A.
Beti-Fang cluster
The Beti-Fang cluster is a group of closely related Bantu languages spoken primarily in Cameroon, Equatorial Guinea, and neighboring Central African regions.
-
B.
Laizo-Falam cluster
The Laizo-Falam cluster is a group of closely related dialects of the Falam Chin language spoken by Chin communities in western Myanmar.
-
C.
Kulisusu–Koroni cluster
The Kulisusu–Koroni cluster is a subgroup of closely related Austronesian languages spoken in southeastern Sulawesi, Indonesia.
-
D.
Berta cluster
Berta cluster is a group of closely related Berta languages spoken primarily in the border regions of Sudan and Ethiopia.
-
E.
Jewel Box cluster
The Jewel Box cluster is a bright and colorful open star cluster in the constellation Crux, renowned for its striking mix of blue and red stars visible even in small telescopes.
- 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_69d81c645c5c8190b1fd16a285a1b78a |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2ed5cfd0819085b9c860b119a9de |
completed | April 14, 2026, 12:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbaca7bbd88190a377d3b74f3d6224 |
completed | May 6, 2026, 9:03 p.m. |
| NEDg | Description generation | batch_69fbae6691b48190a0affc662cbb2d4e |
completed | May 6, 2026, 9:11 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fbaf702c94819095347e2599ae9931 |
completed | May 6, 2026, 9:15 p.m. |
Created at: April 9, 2026, 10:19 p.m.