Triple
T2739141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OKH (Oberkommando des Heeres) |
E60705
|
entity |
| Predicate | hadSection |
P37078
|
FINISHED |
| Object | operations staff |
—
|
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: operations staff | Statement: [OKH (Oberkommando des Heeres), hadSection, operations staff]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadSection Context triple: [OKH (Oberkommando des Heeres), hadSection, operations staff]
-
A.
hasSect
Indicates that an entity includes, contains, or is associated with a particular sect or subgroup within a larger religious, ideological, or organizational context.
-
B.
hasSectionIn
chosen
Indicates that one entity contains or includes another entity as a section or subdivision within it.
-
C.
hadOrgan
Indicates that an entity previously possessed or contained a specific organ as part of its body.
-
D.
hadNo
Indicates that one entity completely lacked or did not possess another entity, attribute, or relationship.
-
E.
hasHad
Indicates that an entity previously experienced, possessed, or was involved in something at some point in the past.
- 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_69ab4b77febc819095603eb012cd141b |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdb2da94c8190bc9d23262e3dfc07 |
completed | March 7, 2026, 8 a.m. |
| PD | Predicate disambiguation | batch_69abd82859348190bce3be8f2e9d60ba |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:56 p.m.