Triple
T35871567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OSCE Special Monitoring Mission to Ukraine |
E1037238
|
entity |
| Predicate | monitoringTools |
P15245
|
FINISHED |
| Object | ground patrols |
—
|
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: ground patrols | Statement: [OSCE Special Monitoring Mission to Ukraine, monitoringTools, ground patrols]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: monitoringTools Context triple: [OSCE Special Monitoring Mission to Ukraine, monitoringTools, ground patrols]
-
A.
monitoringFramework
Indicates that one entity provides or defines a system or structure used to observe, measure, and track the performance or state of another entity or process.
-
B.
inQuadrant
Indicates that one entity is located within a specific quadrant or sector of a defined spatial or coordinate system relative to another reference.
-
C.
mediaMarketRank
Indicates the relative position or ranking of a media market compared to other media markets, typically based on size, reach, or audience metrics.
-
D.
oversightTools
chosen
Indicates that certain tools or mechanisms are used to monitor, review, or supervise the actions or performance of an entity.
-
E.
trafficShare
Indicates the proportion of total traffic or visits that one entity receives relative to others within a defined context or time period.
- 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_69f76e1e701c8190a4990d4978ce4fe6 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7ac23d1388190bdf9628b294943bd |
completed | May 3, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69f7ab734d848190a84f9b8c3a952b75 |
completed | May 3, 2026, 8:09 p.m. |
Created at: May 3, 2026, 4:06 p.m.