Triple
T35695936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King U of Goryeo |
E1031438
|
entity |
| Predicate | relationshipToYiSeongGye |
P207101
|
FINISHED |
| Object | deposed by Yi Seong-gye |
—
|
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: deposed by Yi Seong-gye | Statement: [King U of Goryeo, relationshipToYiSeongGye, deposed by Yi Seong-gye]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToYiSeongGye Context triple: [King U of Goryeo, relationshipToYiSeongGye, deposed by Yi Seong-gye]
-
A.
relationshipToSeongGiHun
Indicates the type or nature of the relationship an entity has with Seong Gi-hun.
-
B.
relationshipWithSeongGiHun
Indicates having some form of personal or social connection with Seong Gi-hun.
-
C.
relationshipToYukina
Indicates a specified type of personal or social connection that an entity has with Yukina.
-
D.
relationshipToUsnavi
Indicates the type or nature of the relationship that an entity has with Usnavi.
-
E.
relationshipToArichAnpin
Indicates a relational connection or association that an entity has to Arich Anpin within a given spiritual, hierarchical, or conceptual framework.
- F. None of above. chosen
Provenance (4 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_69f76e0c73ec819080ab60a9e2f5f1f6 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c92f03c8190ae2751270b195423 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a04d8348190a4819666eab42c9b |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c82179081908325a59b8539b3a8 |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:05 p.m.