Triple
T411367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ouvrage Schoenenbourg |
E9495
|
entity |
| Predicate | garrisonSize |
P13142
|
FINISHED |
| Object | approximately 600 men |
—
|
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: approximately 600 men | Statement: [Ouvrage Schoenenbourg, garrisonSize, approximately 600 men]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: garrisonSize Context triple: [Ouvrage Schoenenbourg, garrisonSize, approximately 600 men]
-
A.
garrisonLabel
Indicates the designation or identifying label assigned to a military garrison associated with an entity.
-
B.
garrisonDuringFormation
Indicates that a military unit is stationed in a specific garrison location during its period of formation or initial organization.
-
C.
typeOfTroops
Indicates the specific category or kind of military forces involved in or associated with an entity or event.
-
D.
countryOfGarrison
Indicates the country in which a military unit, base, or garrison is stationed or based.
-
E.
fleetSize
Indicates the total number of vehicles, vessels, or units that collectively make up a fleet associated with an entity.
- F. None of above. chosen
Provenance (4 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_69a2e80111fc8190961d5b7c6154123f |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ed31681c8190ac32334562fb17fd |
completed | Feb. 28, 2026, 1:27 p.m. |
| PD | Predicate disambiguation | batch_69a2e9737694819080fde9adcc1aa4d4 |
completed | Feb. 28, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69a2ed3032148190beb3a516e437f8f8 |
completed | Feb. 28, 2026, 1:27 p.m. |
Created at: Feb. 28, 2026, 1:09 p.m.