Triple
T24076641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gimhae Kim clan |
E596379
|
entity |
| Predicate | associatedPlaceOfOrigin |
P3743
|
FINISHED |
| Object | Gimhae, South Korea |
—
|
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: Gimhae, South Korea | Statement: [Gimhae Kim clan, associatedPlaceOfOrigin, Gimhae, South Korea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedPlaceOfOrigin Context triple: [Gimhae Kim clan, associatedPlaceOfOrigin, Gimhae, South Korea]
-
A.
placeOfOrigin
chosen
Indicates the location or source from which an entity originally comes or was created.
-
B.
speciesOrigin
Indicates the place, environment, or source from which a species originally arose or evolved.
-
C.
countryOfOrigin
Indicates the country from which an entity originally comes or was first produced, created, or established.
-
D.
historicalOriginCountry
Indicates the country from which something originally came or first emerged in a historical context.
-
E.
capitalOfOrigin
Indicates that one entity is the capital city associated with the origin (such as birthplace, founding place, or source location) of another entity.
- 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_69e288c3999c8190809b282a04813dec |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1db1e959c81909f4365b5d7f934d9 |
completed | April 29, 2026, 10:19 a.m. |
| PD | Predicate disambiguation | batch_69f1764b1d4c8190b12590c6339c31c1 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:42 p.m.