Triple
T19471892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kuba dialect |
E487141
|
entity |
| Predicate | hasAncestor |
P369
|
FINISHED |
| Object |
Proto-Lezgic
Proto-Lezgic is the reconstructed common ancestor of the Lezgic branch of Northeast Caucasian languages, from which varieties such as the Kuba dialect ultimately developed.
|
E1378246
|
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: Proto-Lezgic | Statement: [Kuba dialect, hasAncestor, Proto-Lezgic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Proto-Lezgic Context triple: [Kuba dialect, hasAncestor, Proto-Lezgic]
-
A.
Proto-Gur
Proto-Gur is the reconstructed common ancestor of the Gur languages of West Africa, inferred through comparative linguistic analysis.
-
B.
Proto-Dargwa
Proto-Dargwa is the reconstructed ancestral language from which the modern Dargwa varieties of the Northeast Caucasian language family are derived.
-
C.
Proto-Koman
Proto-Koman is the reconstructed ancestral language from which the modern Koman languages of the Nilo-Saharan family are derived.
-
D.
Proto-Daju language
Proto-Daju language is the reconstructed common ancestor of the Daju languages, hypothesized through comparative linguistic analysis.
-
E.
Proto-Mari
Proto-Mari is the reconstructed ancestral language from which the modern Hill Mari language developed.
- 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: Proto-Lezgic Triple: [Kuba dialect, hasAncestor, Proto-Lezgic]
Generated description
Proto-Lezgic is the reconstructed common ancestor of the Lezgic branch of Northeast Caucasian languages, from which varieties such as the Kuba dialect ultimately developed.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Proto-Lezgic Target entity description: Proto-Lezgic is the reconstructed common ancestor of the Lezgic branch of Northeast Caucasian languages, from which varieties such as the Kuba dialect ultimately developed.
-
A.
Proto-Gur
Proto-Gur is the reconstructed common ancestor of the Gur languages of West Africa, inferred through comparative linguistic analysis.
-
B.
Proto-Dargwa
Proto-Dargwa is the reconstructed ancestral language from which the modern Dargwa varieties of the Northeast Caucasian language family are derived.
-
C.
Proto-Koman
Proto-Koman is the reconstructed ancestral language from which the modern Koman languages of the Nilo-Saharan family are derived.
-
D.
Proto-Daju language
Proto-Daju language is the reconstructed common ancestor of the Daju languages, hypothesized through comparative linguistic analysis.
-
E.
Proto-Mari
Proto-Mari is the reconstructed ancestral language from which the modern Hill Mari language developed.
- 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_69d8e8d924388190b847cb15bb3d0aff |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633e8d9188190a4939f03bad89add |
completed | April 20, 2026, 2:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07404fd4348190bc2efbebc7828716 |
completed | May 15, 2026, 3:48 p.m. |
| NEDg | Description generation | batch_6a074155addc8190a80e37d8f9d537a8 |
completed | May 15, 2026, 3:52 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0741e454a48190ac03aa458ca2b3b3 |
completed | May 15, 2026, 3:55 p.m. |
Created at: April 10, 2026, 1:39 p.m.