Triple
T973656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mounted Unit |
E21000
|
entity |
| Predicate | mayCollaborateWith |
P10645
|
FINISHED |
| Object | patrol division |
—
|
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: patrol division | Statement: [Mounted Unit, mayCollaborateWith, patrol division]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayCollaborateWith Context triple: [Mounted Unit, mayCollaborateWith, patrol division]
-
A.
isCollaboration
chosen
Indicates that two or more entities are jointly working together toward a shared goal or producing something in partnership.
-
B.
canBeConvenedBy
Indicates that an entity (such as a group, body, or meeting) may be formally brought together or assembled by a specified agent or authority.
-
C.
mayMeet
Indicates that one entity is permitted or has the possibility to meet or come together with another entity.
-
D.
hasCoauthor
Indicates that two or more entities have jointly authored the same work or publication.
-
E.
wouldProvide
Indicates that one entity is willing or expected to supply or furnish something to another entity under certain conditions.
- 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_69a493c2b62c8190b616351789ec47f8 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b45f28f081908d41b2d7f353708d |
completed | March 1, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69a4b2a6aa2c8190aebba71320ab678f |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.