Triple
T22231074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coastal Line |
E549466
|
entity |
| Predicate | connectsCity |
P4245
|
FINISHED |
| Object | Matara |
—
|
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: Matara | Statement: [Coastal Line, connectsCity, Matara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matara Context triple: [Coastal Line, connectsCity, Matara]
-
A.
Matara
chosen
Matara is a major coastal city in southern Sri Lanka known for its historic fort, beaches, and role as a regional commercial and transport hub.
-
B.
Matara District
Matara District is an administrative district in southern Sri Lanka known for its coastal cities, historical sites, and agricultural hinterland.
-
C.
Matara, Sri Lanka
Matara, Sri Lanka is a major coastal city in the Southern Province known for its historic fort, beaches, and role as a regional commercial and cultural hub.
-
D.
Unawatuna
Unawatuna is a popular coastal town in southern Sri Lanka known for its palm-fringed beach, coral-rich bay, and laid-back tourist atmosphere.
-
E.
Malabe
Malabe is a rapidly developing suburb in the Colombo District of Sri Lanka, known for its IT parks, private universities, and growing residential communities.
- 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_69e11e4102b881909cf47d3768e25c19 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12bf2a26c81908aaf614d7c75e219 |
completed | April 28, 2026, 9:51 p.m. |
Created at: April 16, 2026, 8:38 p.m.