Triple
T29901384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Depositary Notifications (CN series) |
E759415
|
entity |
| Predicate | coversAction |
P56248
|
FINISHED |
| Object | signature of treaties |
—
|
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: signature of treaties | Statement: [Depositary Notifications (CN series), coversAction, signature of treaties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coversAction Context triple: [Depositary Notifications (CN series), coversAction, signature of treaties]
-
A.
coversActionType
chosen
Indicates that one entity’s scope, responsibility, or applicability includes or encompasses a particular type of action.
-
B.
coversFrom
Indicates that one entity provides protection, concealment, or shelter for another entity against something originating from a specified source or direction.
-
C.
coversForm
Indicates that one entity extends over or encloses the surface or outer form of another entity.
-
D.
coverStatus
Indicates the current state or condition of coverage that applies to an entity, such as whether coverage is active, pending, expired, or otherwise classified.
-
E.
coversTo
Indicates that one entity extends its coverage or protective scope to include 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_69f224600590819085e148a01c056ef6 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f727afd5d88190ad48735cd1b32787 |
completed | May 3, 2026, 10:47 a.m. |
| PD | Predicate disambiguation | batch_69f72737c42c8190a3f781a5e98868ff |
completed | May 3, 2026, 10:45 a.m. |
Created at: April 29, 2026, 6:06 p.m.