Triple
T27665885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krüger |
E697225
|
entity |
| Predicate | wordFormation |
P75423
|
FINISHED |
| Object | "Krug" + agentive suffix "-er" |
—
|
NE NERFINISHED |
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: "Krug" + agentive suffix "-er" | Statement: [Krüger, wordFormation, "Krug" + agentive suffix "-er"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wordFormation Context triple: [Krüger, wordFormation, "Krug" + agentive suffix "-er"]
-
A.
typicalWordFormation
Indicates the usual or most common way in which a word is formed from other linguistic elements (such as roots, affixes, or compounds).
-
B.
hasWordFormation
chosen
Indicates that one linguistic unit is formed or derived from another through a specific word-formation process (such as compounding, derivation, or affixation).
-
C.
compositionalForm
Indicates the structural or formal composition that defines how parts are organized or combined within something.
-
D.
hasPrimaryWordFormationProcess
Indicates that one entity is the main or predominant word-formation process by which another entity (typically a word or lexical item) is formed.
-
E.
isCombinedFormOf
Indicates that one entity is a composite or merged form that results from combining two or more other entities.
- 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_69ef590b85a4819083ec7c12bd3c9c10 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f634a401e08190b2144d47f1df15e0 |
completed | May 2, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:38 p.m.