Triple
T25333595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bunopithecus |
E635216
|
entity |
| Predicate | fossilBasis |
P158204
|
FINISHED |
| Object | mandibular remains |
—
|
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: mandibular remains | Statement: [Bunopithecus, fossilBasis, mandibular remains]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fossilBasis Context triple: [Bunopithecus, fossilBasis, mandibular remains]
-
A.
fossilBasis
chosen
Indicates that the relationship or claim is supported or evidenced specifically by fossil remains.
-
B.
fossilGroup
Indicates that one entity is classified as belonging to a particular fossil group or assemblage associated with another entity.
-
C.
fossilContent
Indicates that one entity contains, preserves, or is characterized by the fossils of another entity.
-
D.
fossilMorphology
Indicates that one entity describes or characterizes the physical form and structural features of a fossil associated with another entity.
-
E.
fossilRecordType
Indicates the classification of how a fossil is preserved or represented in the geological record (e.g., body fossil, trace fossil, cast, mold).
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f497c80e0881908227999fa2c4e0d6 |
completed | May 1, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 1:31 p.m.