Triple
T35689098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teufelhunden |
E1031239
|
entity |
| Predicate | hasGenderInGerman |
P169327
|
FINISHED |
| Object | masculine plural form |
—
|
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: masculine plural form | Statement: [Teufelhunden, hasGenderInGerman, masculine plural form]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGenderInGerman Context triple: [Teufelhunden, hasGenderInGerman, masculine plural form]
-
A.
genderInGerman
chosen
Indicates that a given entity has a specified grammatical gender in the German language.
-
B.
hasGenderInPolish
Indicates that an entity has a specific grammatical gender when expressed in the Polish language.
-
C.
hasGenderInPortuguese
Indicates that a term or entity is associated with a specific grammatical gender in the Portuguese language.
-
D.
hasGenderOfPerson
Indicates that a person is associated with a specific gender classification.
-
E.
hasGenderInCatalan
Indicates that a given entity has a specific grammatical gender when expressed in the Catalan language.
- 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_69f76e0c73ec819080ab60a9e2f5f1f6 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fdb45537288190b6791078d4a6899f |
completed | May 8, 2026, 10 a.m. |
| PD | Predicate disambiguation | batch_69fdb39ad96481908376d7def9fafc13 |
completed | May 8, 2026, 9:57 a.m. |
Created at: May 3, 2026, 4:05 p.m.