Triple
T22467008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Candidasa |
E555381
|
entity |
| Predicate | isAlternativeTo |
P5887
|
FINISHED |
| Object | Seminyak |
—
|
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: Seminyak | Statement: [Candidasa, isAlternativeTo, Seminyak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Seminyak Context triple: [Candidasa, isAlternativeTo, Seminyak]
-
A.
Seminyak
chosen
Seminyak is an upscale beach resort area on Bali known for its luxury hotels, trendy restaurants, boutiques, and vibrant nightlife.
-
B.
Legian
Legian is a popular beach resort area on Bali’s southwest coast, known for its surfing-friendly waves, lively nightlife, and proximity to Kuta and Seminyak.
-
C.
Canggu
Canggu is a trendy coastal village in Bali known for its surf-friendly beaches, laid-back atmosphere, and vibrant café and nightlife scene.
-
D.
Sanur
Sanur is a coastal town in southeastern Bali known for its tranquil beaches, laid-back atmosphere, and role as one of the island’s earliest resort destinations.
-
E.
Senggigi
Senggigi is a popular coastal resort town on the Indonesian island of Lombok, known for its long sandy beaches, sunset views, and access to nearby islands and dive sites.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b84e4a88190b6fbfdbd754ba1c5 |
completed | April 29, 2026, 1:14 a.m. |
Created at: April 16, 2026, 8:48 p.m.