Triple
T1590938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Committee (Disarmament and International Security) |
E34175
|
entity |
| Predicate | usesDocuments |
P3129
|
FINISHED |
| Object | Draft resolutions |
—
|
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: Draft resolutions | Statement: [First Committee (Disarmament and International Security), usesDocuments, Draft resolutions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesDocuments Context triple: [First Committee (Disarmament and International Security), usesDocuments, Draft resolutions]
-
A.
usedDocument
chosen
Indicates that one entity has employed, referenced, or otherwise made use of a particular document in performing an action or fulfilling a purpose.
-
B.
documentTypeUsed
Indicates that a particular type or category of document is employed or applied in a given context or activity.
-
C.
documentedBy
Indicates that something is recorded, described, or evidenced in a specific document or set of documents.
-
D.
supportsDocument
Indicates that one entity provides compatibility or functionality for handling, processing, or using a particular document or document type.
-
E.
usedInOfficialDocumentsOf
Indicates that something (e.g., a term, symbol, or format) is employed within the formal or legally recognized documents issued by a particular entity or jurisdiction.
- 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_69a885fceb2c8190b47e0f7c0aefbff0 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a93aedd45c819085843ac843d640e8 |
completed | March 5, 2026, 8:12 a.m. |
| PD | Predicate disambiguation | batch_69a907bdc19081908c84c5c0aa09e282 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:27 p.m.