Triple
T8914358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Melanospiza |
E212259
|
entity |
| Predicate | vernacularGroup |
P86353
|
FINISHED |
| Object | seedeaters |
—
|
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: seedeaters | Statement: [Melanospiza, vernacularGroup, seedeaters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vernacularGroup Context triple: [Melanospiza, vernacularGroup, seedeaters]
-
A.
vernacularGrouping
Indicates a relationship where entities are grouped together based on a shared vernacular, such as common local language, dialect, or colloquial naming.
-
B.
linguisticSubgroup
Indicates that one linguistic group forms a subordinate or specialized subset within a larger linguistic group or family.
-
C.
linguisticArea
Indicates a regional context in which languages share features due to geographic proximity and contact rather than common genetic origin.
-
D.
majorLanguageGroupOf
Indicates that one language group is the primary or dominant linguistic classification to which another language or set of languages belongs.
-
E.
linguisticVariant
Indicates that one linguistic form is an alternative version or expression of another within the same or closely related language context.
- F. None of above. chosen
Provenance (4 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_69ca8393b1808190bd4336787ffa2c40 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc660e620c8190b02b9843c8f02bfa |
completed | April 1, 2026, 12:25 a.m. |
| PD | Predicate disambiguation | batch_69cc5ecf55248190a29f00fbf99f13c4 |
completed | March 31, 2026, 11:54 p.m. |
| PDg | Predicate description generation | batch_69cc604965c48190bbb6db0ae8108e67 |
completed | April 1, 2026, 12:01 a.m. |
Created at: March 30, 2026, 6:56 p.m.