Triple
T10923062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Collective Security Treaty |
E257994
|
entity |
| Predicate | providesCollectiveDefense |
P32971
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Collective Security Treaty, providesCollectiveDefense, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providesCollectiveDefense Context triple: [Collective Security Treaty, providesCollectiveDefense, yes]
-
A.
hasPeacekeepingForcesFrom
Indicates that an entity hosts or is supported by peacekeeping forces that originate from another specified entity.
-
B.
partyForDefense
Indicates a legal relationship where an entity serves as or is designated as the defending party in a legal proceeding or dispute.
-
C.
militaryCooperation
chosen
Indicates a collaborative relationship in which entities coordinate, support, or jointly conduct military activities, operations, or planning.
-
D.
NATOCategory
Indicates that an entity is classified according to a specific NATO-defined category or designation.
-
E.
sharesBorderDefenseWith
Indicates that two entities cooperate or coordinate in protecting and defending their shared border.
- 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_69d6aa864ed88190818280ab6791d065 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7708e3fd881908da10f24a856364c |
completed | April 9, 2026, 9:25 a.m. |
| PD | Predicate disambiguation | batch_69d72e799f808190b6ab64fc7586a303 |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:22 p.m.