Triple
T23910655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danuri |
E601928
|
entity |
| Predicate | firstOfCountry |
P59622
|
FINISHED |
| Object | first South Korean lunar orbiter |
—
|
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: first South Korean lunar orbiter | Statement: [Danuri, firstOfCountry, first South Korean lunar orbiter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstOfCountry Context triple: [Danuri, firstOfCountry, first South Korean lunar orbiter]
-
A.
firstForCountry
chosen
Indicates that the subject is the first instance or occurrence of its type to happen or exist within the specified country.
-
B.
firstMatchCountry
Indicates that the referenced country is the first one that matches a given set of criteria or conditions among a group of countries.
-
C.
firstHolderCountry
Indicates the country that initially held or possessed the referenced entity before any subsequent transfers or changes in ownership.
-
D.
mainCountry
Indicates that one country is the primary or most significant country associated with a given entity or context.
-
E.
primaryRouteCountry
Indicates the country that serves as the main or principal route location associated with the subject.
- 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_69e2953a187081908346a9f36e85fc98 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1ce94f65c8190807723344fa0b837 |
completed | April 29, 2026, 9:25 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:38 p.m.