Triple
T13945455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 43rd Reconnaissance Regiment |
E335368
|
entity |
| Predicate | divisionTypeSupported |
P97449
|
FINISHED |
| Object | infantry 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: infantry division | Statement: [43rd Reconnaissance Regiment, divisionTypeSupported, infantry division]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: divisionTypeSupported Context triple: [43rd Reconnaissance Regiment, divisionTypeSupported, infantry division]
-
A.
divisionTypeServedWith
chosen
Indicates the type of organizational division that is served or supported in conjunction with a given entity or service.
-
B.
typeOfDivision
Indicates the specific category or kind of division that characterizes how something is separated, organized, or partitioned.
-
C.
divisionIncluded
Indicates that one division is contained within or forms a part of another division.
-
D.
divisionFormat
Indicates the specific structural or organizational format in which a division or subdivision is arranged or presented.
-
E.
hasNumberOfDivisions
Indicates the relationship that specifies how many divisions or subunits an entity possesses.
- 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_69d81c6081b88190b53e317c3370c8fe |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e10f60c81908ee9636e85c070ff |
completed | April 14, 2026, 12:07 p.m. |
| PD | Predicate disambiguation | batch_69de05a3ccf88190b45c742db483fa08 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:17 p.m.