Triple
T21509837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | China–North Korea relations |
E530686
|
entity |
| Predicate | treatyFeature |
P144666
|
FINISHED |
| Object | mutual defense clause |
—
|
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: mutual defense clause | Statement: [China–North Korea relations, treatyFeature, mutual defense clause]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treatyFeature Context triple: [China–North Korea relations, treatyFeature, mutual defense clause]
-
A.
treatyOf
Indicates a formal agreement or pact established between entities, typically states or organizations, defining their mutual obligations or terms.
-
B.
treatyFocus
Indicates that a treaty is primarily concerned with, directed toward, or centered on a particular subject, issue, or area.
-
C.
treatyFamily
Indicates that there exists a familial or kinship-based treaty or formal agreement relationship between the entities.
-
D.
treaty
Indicates a formal, negotiated agreement or pact established between entities, typically states or organizations, that defines mutual obligations, rights, or terms of cooperation.
-
E.
treatyType
Indicates the specific category or classification of a treaty that characterizes the nature of the agreement between parties.
- 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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea84dfbc8190a23d9a7d6eb2c2b5 |
completed | April 23, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69e631f6e68081908f5ee4ce7413803e |
completed | April 20, 2026, 2:02 p.m. |
| PDg | Predicate description generation | batch_69e6386c5a4481909c37f7de7e9fc025 |
completed | April 20, 2026, 2:30 p.m. |
Created at: April 16, 2026, 6:25 p.m.