Triple
T547420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port Blair |
E12762
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Telugu |
E5056
|
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: Telugu | Statement: [Port Blair, language, Telugu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Telugu Context triple: [Port Blair, language, Telugu]
-
A.
Telugu
chosen
Telugu is a major Dravidian language predominantly spoken in the Indian states of Andhra Pradesh and Telangana, known for its rich literary tradition and classical status.
-
B.
Rayalaseema Telugu
Rayalaseema Telugu is a regional dialect of the Telugu language spoken primarily in the Rayalaseema region of Andhra Pradesh, characterized by distinct phonetic and lexical features.
-
C.
Kannada
Kannada is a major Dravidian language predominantly spoken in the Indian state of Karnataka and surrounding regions, with a rich literary tradition spanning over a millennium.
-
D.
Tamil
Tamil is a classical Dravidian language spoken predominantly in the Indian state of Tamil Nadu and in parts of Sri Lanka, with a rich literary tradition spanning over two millennia.
-
E.
Hindi
Hindi is an Indo-Aryan language widely spoken across northern and central India and used in government, education, media, and popular culture.
- 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_69a49334226c81908b0ea1689ef6aa3f |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a498e2e8c88190a66d759ed3094e18 |
completed | March 1, 2026, 7:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a4e02e0c1c81908fcb5356dc2b8f97 |
completed | March 2, 2026, 12:56 a.m. |
Created at: March 1, 2026, 7:32 p.m.