Triple
T7912261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johann Friedrich Gmelin |
E183726
|
entity |
| Predicate | standardFormInZoology |
P1329
|
FINISHED |
| Object | Gmelin, 1788 |
—
|
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: Gmelin, 1788 | Statement: [Johann Friedrich Gmelin, standardFormInZoology, Gmelin, 1788]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: standardFormInZoology Context triple: [Johann Friedrich Gmelin, standardFormInZoology, Gmelin, 1788]
-
A.
speciesForm
Indicates that one entity is a specific biological form, variant, or manifestation of a species represented by another entity.
-
B.
scientificName
chosen
Indicates the formal taxonomic name assigned to an organism according to scientific naming conventions.
-
C.
frozenZooDescription
Indicates that an entity provides a description or summary of a frozen zoo, typically detailing its preserved biological specimens or related information.
-
D.
zoonMeans
Indicates that one entity expresses, defines, or conveys the meaning of another entity.
-
E.
animalForm
Indicates that one entity takes the shape, body, or characteristics of an animal.
- 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_69ca828dec0c81908b8f55a4dbbb53ff |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a7383cc819084eab19799209d2e |
completed | March 31, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69cae92f9498819085277879e59aa072 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:04 p.m.