Triple
T457469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stalags |
E7263
|
entity |
| Predicate | termDerivedFrom |
P909
|
FINISHED |
| Object | Stammlager (main camp) |
—
|
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: Stammlager (main camp) | Statement: [Stalags, termDerivedFrom, Stammlager (main camp)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: termDerivedFrom Context triple: [Stalags, termDerivedFrom, Stammlager (main camp)]
-
A.
derivedFrom
chosen
Indicates that one entity originates, is obtained, or is developed from another source entity.
-
B.
differentiatedFrom
Indicates that one entity is distinguished or set apart from another by identifying differences between them.
-
C.
termType
Indicates the classification or category of a term within a system, specifying what kind of term it is (e.g., type, role, or function) in relation to others.
-
D.
titleDerivedFrom
Indicates that the title of one entity is obtained or adapted from another entity.
-
E.
derivationType
Indicates the specific manner or process by which one entity is derived or obtained from another.
- 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_69a2e7e5c5bc8190a1dc8178218fba40 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2efa1616481909399f92551a0c9e3 |
completed | Feb. 28, 2026, 1:37 p.m. |
| PD | Predicate disambiguation | batch_69a2ede614b88190be07425f5535f56d |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.