Triple
T24056805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paranthropus boisei |
E595828
|
entity |
| Predicate | typeSpecimenCountry |
P86127
|
FINISHED |
| Object | Tanzania |
—
|
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: Tanzania | Statement: [Paranthropus boisei, typeSpecimenCountry, Tanzania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeSpecimenCountry Context triple: [Paranthropus boisei, typeSpecimenCountry, Tanzania]
-
A.
hasCountryOfCollection
chosen
Indicates the country in which an item, specimen, or object was collected.
-
B.
countryOfProtectedArea
Indicates that a protected natural area is located within and legally belongs to a specific country.
-
C.
designationCountry
Indicates the country that officially assigns or confers a particular status, title, or designation on an entity.
-
D.
countryOfReferent
Indicates that one entity is the country with which the referenced entity (the referent) is associated or to which it belongs.
-
E.
countryOf
Indicates that one entity is the country to which another entity belongs, is located in, or is associated with.
- 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_69e288c184b081909f1f1751fb8e299a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1da50d6108190a36bffaa475c8b93 |
completed | April 29, 2026, 10:15 a.m. |
| PD | Predicate disambiguation | batch_69f1764b1d4c8190b12590c6339c31c1 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:34 p.m.