Triple
T19433209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarama |
E486166
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Lanka |
—
|
NE NERFINISHED |
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: Lanka | Statement: [Sarama, residence, Lanka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lanka Context triple: [Sarama, residence, Lanka]
-
A.
Lanka
chosen
Lanka is the island kingdom in the Ramayana epic ruled by the demon king Ravana, where Sita is held captive and Rama wages war to rescue her.
-
B.
Sri Lanka
Sri Lanka is an island nation in the Indian Ocean known for its rich cultural heritage, diverse landscapes, and strategic location off the southern coast of India.
-
C.
Wat Lanka
Wat Lanka is one of Phnom Penh’s oldest and most significant Buddhist temples, known for its traditional Khmer architecture and religious importance.
-
D.
Mattumagala, Sri Lanka
Mattumagala, Sri Lanka is a locality best known as the birthplace of renowned Sri Lankan fast bowler Chaminda Vaas.
-
E.
Walpola, Sri Lanka
Walpola, Sri Lanka is a village in Sri Lanka notable as the birthplace of the renowned Buddhist monk and scholar Walpola Rahula.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d7ad488190a3373045029b0f3b |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6335dae10819096e1825741f814ed |
completed | April 20, 2026, 2:08 p.m. |
Created at: April 10, 2026, 1:37 p.m.