Triple
T20747379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Raja Ampat Islands |
E510620
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Salawati |
—
|
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: Salawati | Statement: [Raja Ampat Islands, hasPart, Salawati]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salawati Context triple: [Raja Ampat Islands, hasPart, Salawati]
-
A.
Salawati
chosen
Salawati is a large island in Indonesia’s Papuan Islands region, known for its rich biodiversity and proximity to the renowned Raja Ampat archipelago.
-
B.
Lasalimu
Lasalimu is a coastal town and district in Southeast Sulawesi, Indonesia, known as a local administrative and transit area in the region.
-
C.
Saryati
Saryati is a figure in Hindu mythology known as one of the sons of the progenitor Shraddhadeva Manu and a king mentioned in ancient texts.
-
D.
Sawila
Sawila is a Papuan language spoken on Alor Island in eastern Indonesia, known for its complex verb morphology and membership in the Alor–Pantar language family.
-
E.
Karimah
Karimah is a feminine given name of Arabic origin meaning "generous" or "noble."
- 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_69e0b4c845e88190b4c5f3ae79291182 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c226fbf881909794eff3ee9e206b |
completed | April 21, 2026, 12:17 a.m. |
Created at: April 16, 2026, 12:33 p.m.