Triple
T19216918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Segitiga Terumbu Karang |
E480509
|
entity |
| Predicate | memilikiBentuk |
P109283
|
FINISHED |
| Object | segitiga secara geografis |
—
|
LITERAL FINISHED |
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: segitiga secara geografis | Statement: [Segitiga Terumbu Karang, memilikiBentuk, segitiga secara geografis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memilikiBentuk Context triple: [Segitiga Terumbu Karang, memilikiBentuk, segitiga secara geografis]
-
A.
shaped
Indicates that one entity has given form, contour, or structure to another entity or outcome.
-
B.
shapeType
chosen
Indicates the specific geometric form or category that characterizes an entity’s shape.
-
C.
الشكل
Indicates a relationship where one entity represents, takes, or describes the form, shape, or configuration of another entity.
-
D.
shape
Indicates that one entity has a particular geometric or physical form characterized by the other entity.
-
E.
hasBillShape
Indicates that one entity has a bill whose shape matches the specified form or category.
- F. None of above.
Provenance (3 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_69d8e8cb8c348190b52075823911c869 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fa3aff9c8190974363683b8246f5 |
completed | April 20, 2026, 10:04 a.m. |
| PD | Predicate disambiguation | batch_69e4dcf22b3c8190bee02e3af946e114 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:23 p.m.