Triple
T3506443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Special Training School 103 |
E74085
|
entity |
| Predicate | targetPersonnel |
P13472
|
FINISHED |
| Object | SOE agents |
—
|
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: SOE agents | Statement: [Special Training School 103, targetPersonnel, SOE agents]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetPersonnel Context triple: [Special Training School 103, targetPersonnel, SOE agents]
-
A.
peakPersonnel
Indicates the maximum number of personnel involved or present at any point during a specified period or activity.
-
B.
personnelType
Indicates the classification or role category assigned to a person within an organization or system.
-
C.
targetCandidate
chosen
Indicates that an entity is being considered or designated as a potential target for selection, action, or further evaluation.
-
D.
targetsGroup
Indicates that an action, influence, or effect is directed toward a specific group as its intended recipient or focus.
-
E.
authorizedPersonnel
Indicates that the referenced entity is officially permitted or empowered to access, use, or perform actions within a specified system, resource, or context.
- 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_69ad85ce7a9c81909ddc5cf0cb67a6e3 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbbf52bd8819085a2ac5f48cc5c68 |
completed | March 8, 2026, 6:12 p.m. |
| PD | Predicate disambiguation | batch_69adae0e770481908528fa35eda53003 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:18 p.m.