Triple
T8550004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamilakam |
E202421
|
entity |
| Predicate | majorPort |
P528
|
FINISHED |
| Object | Korkai |
E639729
|
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: Korkai | Statement: [Tamilakam, majorPort, Korkai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Korkai Context triple: [Tamilakam, majorPort, Korkai]
-
A.
Korkai
chosen
Korkai was an ancient port city in southern India that served as an early capital and major maritime trade center of the Pandya kingdom.
-
B.
Keelakarai
Keelakarai is a coastal town in Tamil Nadu, India, known for its historic mosques, maritime trading heritage, and culturally rich Muslim community.
-
C.
Hogenakkal
Hogenakkal is a small town in Tamil Nadu, India, known as the gateway to the famous Hogenakkal Falls on the Kaveri River.
-
D.
Kakdwip
Kakdwip is a town in West Bengal, India, known as a riverine and coastal hub near the Bay of Bengal and a gateway to the Sunderbans region.
-
E.
Srirangam Island
Srirangam Island is a river island in Tamil Nadu, India, renowned as a major Hindu pilgrimage center and home to the historic temple town of Srirangam.
- 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_69ca832610e08190b3b6c6cd2c250255 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe75589d8819096177ddbd3dafcb6 |
completed | March 31, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce892efdf8819093c966bd8f6c8065 |
completed | April 2, 2026, 3:20 p.m. |
Created at: March 30, 2026, 6:19 p.m.