Triple
T21781579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Lombok Regency |
E537725
|
entity |
| Predicate | seatOfGovernment |
P761
|
FINISHED |
| Object | Tanjung |
—
|
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: Tanjung | Statement: [North Lombok Regency, seatOfGovernment, Tanjung]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tanjung Context triple: [North Lombok Regency, seatOfGovernment, Tanjung]
-
A.
Tanjung
chosen
Tanjung is a coastal town on the Indonesian island of Lombok that serves as an administrative and commercial hub for the surrounding region.
-
B.
Tanjung Cho
Tanjung Cho is one of the high-altitude glacial lakes in the Gokyo Lakes system of Nepal’s Everest region, known for its striking turquoise waters and dramatic Himalayan surroundings.
-
C.
Tanjung Raya
Tanjung Raya is a district in West Sumatra, Indonesia, known for encompassing the scenic area around Lake Maninjau and its surrounding highland landscapes.
-
D.
Tanjung Aan
Tanjung Aan is a scenic white-sand beach and popular coastal tourist destination on the southern coast of Lombok, Indonesia.
-
E.
Tanjung Bira
Tanjung Bira is a popular beach destination in South Sulawesi, Indonesia, known for its white sand, clear turquoise waters, and diving and snorkeling spots.
- 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_69e0c47198f881908cb0d237266c10e9 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0462db0208190ad31c132d3f875bc |
completed | April 28, 2026, 5:31 a.m. |
Created at: April 16, 2026, 6:52 p.m.