Triple
T2920051
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T-Stoff |
E78696
|
entity |
| Predicate | namingOrigin |
P3325
|
FINISHED |
| Object | German military code designation |
—
|
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: German military code designation | Statement: [T-Stoff, namingOrigin, German military code designation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: namingOrigin Context triple: [T-Stoff, namingOrigin, German military code designation]
-
A.
hasNameOrigin
chosen
Indicates that the origin or source of an entity’s name is specified by the related entity.
-
B.
nameGivesRiseTo
Indicates that one name, term, or designation leads to, causes, or results in the emergence or establishment of another.
-
C.
givenNameFor
Indicates that one entity is the personal first name assigned to or used for another entity.
-
D.
institutionNativeName
Indicates that an institution is associated with its official or commonly used name in the institution’s original or local language.
-
E.
hasAcronymOrigin
Indicates that an acronym is derived from or originates from a specific longer expression or name.
- 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_69ad8b0c2ad081909ff87050ae542bb9 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad97fd89d88190bc7db4b39058ae3a |
completed | March 8, 2026, 3:38 p.m. |
| PD | Predicate disambiguation | batch_69ad9603ddd88190b8bf91bc7517cc21 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:54 p.m.