Triple
T27271160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Homo rudolfensis |
E688054
|
entity |
| Predicate | holotypeFoundAt |
P98594
|
FINISHED |
| Object | Koobi Fora, Kenya |
—
|
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: Koobi Fora, Kenya | Statement: [Homo rudolfensis, holotypeFoundAt, Koobi Fora, Kenya]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holotypeFoundAt Context triple: [Homo rudolfensis, holotypeFoundAt, Koobi Fora, Kenya]
-
A.
holotypeFoundOnPropertyOf
Indicates that the holotype specimen of a taxon was discovered on land owned or controlled by the referenced property holder.
-
B.
holotypeSpecimenFoundNear
chosen
Indicates that the designated holotype specimen of a species was discovered in close geographic proximity to a specified location or feature.
-
C.
holotypeSpecimenNumber
Indicates the identifying specimen number assigned to the holotype that formally defines a taxon in biological classification.
-
D.
holotypeStatus
Indicates that an entity serves as the designated holotype specimen on which the formal description and name of a taxon are based.
-
E.
holotypeRepository
Indicates the institution or collection where the designated holotype specimen of a taxon is stored or curated.
- 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_69ef3558cf8881909595ef89daf6e14a |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f62722eba88190b66a514b023a1197 |
completed | May 2, 2026, 4:32 p.m. |
| PD | Predicate disambiguation | batch_69f620e38aec8190bb184edcdbd6da64 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 10:59 a.m.