Triple
T26962825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bengalese finch |
E679090
|
entity |
| Predicate | nativeRangeOfWildAncestor |
P78307
|
FINISHED |
| Object | South Asia |
—
|
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: South Asia | Statement: [Bengalese finch, nativeRangeOfWildAncestor, South Asia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nativeRangeOfWildAncestor Context triple: [Bengalese finch, nativeRangeOfWildAncestor, South Asia]
-
A.
ancestralRange
chosen
Indicates the geographic area or region that a lineage or taxon historically occupied in its evolutionary past.
-
B.
nativeRange
Indicates the geographic area where an entity naturally occurs or originated without human introduction.
-
C.
nativeRangeType
Indicates the specific type or classification of the geographic area where an entity naturally occurs or originates.
-
D.
ancestralDomainOf
Indicates that one entity is the original or historically prior domain from which another domain is derived or descended.
-
E.
ancestralDomain
Indicates that one entity is the traditional or long-held territory or domain from which another entity originates or to which it is ancestrally connected.
- 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_69eeeb4f3a448190b1e94b2d4776c16e |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f620ede4f88190a98f91af97505663 |
completed | May 2, 2026, 4:06 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:33 a.m.