Triple
T22214489
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ja-Ela |
E549038
|
entity |
| Predicate | hasNearbyTown |
P3883
|
FINISHED |
| Object | Ragama |
—
|
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: Ragama | Statement: [Ja-Ela, hasNearbyTown, Ragama]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ragama Context triple: [Ja-Ela, hasNearbyTown, Ragama]
-
A.
Ragama
chosen
Ragama is a suburban town in Sri Lanka’s Western Province, known as a key residential and transport hub near Colombo.
-
B.
Nagamangala
Nagamangala is a town in the Indian state of Karnataka known for its temples and role as a local commercial and administrative center.
-
C.
Homagama
Homagama is a rapidly developing suburban town in Sri Lanka’s Western Province, situated southeast of central Colombo and known for its residential growth and educational and industrial facilities.
-
D.
Attanagalla
Attanagalla is a historically significant electoral division in Sri Lanka long associated with the influential Bandaranaike political family.
-
E.
Kolonnawa
Kolonnawa is a suburb and urban area in Sri Lanka located within the Colombo metropolitan region.
- 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_69e11e3f7e04819089806d81d5ac431e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b8b13f8819099ed8bebbfea3bc8 |
completed | April 28, 2026, 9:50 p.m. |
Created at: April 16, 2026, 8:37 p.m.