Triple
T1802447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Dravidian |
E39750
|
entity |
| Predicate | includes |
P1393
|
FINISHED |
| Object |
Tamil–Malayalam subgroup
The Tamil–Malayalam subgroup is a branch of the Dravidian language family comprising closely related languages such as Tamil and Malayalam that evolved from a common ancestral tongue in South India.
|
E202769
|
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: Tamil–Malayalam subgroup | Statement: [Southern Dravidian, includes, Tamil–Malayalam subgroup]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tamil–Malayalam subgroup Context triple: [Southern Dravidian, includes, Tamil–Malayalam subgroup]
-
A.
Tamil–Kannada subgroup
The Tamil–Kannada subgroup is a primary branch of the Dravidian language family that encompasses closely related South Indian languages, including Tamil and Kannada, which share a common historical and linguistic ancestry.
-
B.
Kolami–Naiki subgroup
The Kolami–Naiki subgroup is a branch of the Dravidian language family comprising closely related tribal languages spoken primarily in central India.
-
C.
South-Central Dravidian
South-Central Dravidian is a branch of the Dravidian language family that includes languages such as Telugu and related tongues spoken primarily in south-central India.
-
D.
North Dravidian languages
The North Dravidian languages are a small, geographically northern branch of the Dravidian language family spoken mainly in eastern and central India, including languages such as Kurukh and Malto.
-
E.
Proto-South-Central Dravidian
Proto-South-Central Dravidian is the reconstructed ancestral language from which the modern South-Central Dravidian languages, such as Telugu and Gondi, are believed to have descended.
- 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: Tamil–Malayalam subgroup Triple: [Southern Dravidian, includes, Tamil–Malayalam subgroup]
Generated description
The Tamil–Malayalam subgroup is a branch of the Dravidian language family comprising closely related languages such as Tamil and Malayalam that evolved from a common ancestral tongue in South India.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tamil–Malayalam subgroup Target entity description: The Tamil–Malayalam subgroup is a branch of the Dravidian language family comprising closely related languages such as Tamil and Malayalam that evolved from a common ancestral tongue in South India.
-
A.
Tamil–Kannada subgroup
The Tamil–Kannada subgroup is a primary branch of the Dravidian language family that encompasses closely related South Indian languages, including Tamil and Kannada, which share a common historical and linguistic ancestry.
-
B.
Kolami–Naiki subgroup
The Kolami–Naiki subgroup is a branch of the Dravidian language family comprising closely related tribal languages spoken primarily in central India.
-
C.
South-Central Dravidian
South-Central Dravidian is a branch of the Dravidian language family that includes languages such as Telugu and related tongues spoken primarily in south-central India.
-
D.
North Dravidian languages
The North Dravidian languages are a small, geographically northern branch of the Dravidian language family spoken mainly in eastern and central India, including languages such as Kurukh and Malto.
-
E.
Proto-South-Central Dravidian
Proto-South-Central Dravidian is the reconstructed ancestral language from which the modern South-Central Dravidian languages, such as Telugu and Gondi, are believed to have descended.
- 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_69a88632aa588190ba3978fde0db5bbd |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aa656c4c5481908468c6e6f9c4bfc0 |
completed | March 6, 2026, 5:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adbf5645808190a774d96cfe5c5e58 |
completed | March 8, 2026, 6:26 p.m. |
| NEDg | Description generation | batch_69adbff32038819088dffc71e8376821 |
completed | March 8, 2026, 6:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69adc084c9b88190a0d53f5c7c459611 |
completed | March 8, 2026, 6:31 p.m. |
Created at: March 4, 2026, 7:32 p.m.