Triple
T36733854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Ternan |
E907412
|
entity |
| Predicate | fossilsDiscoveredInclude |
P9689
|
FINISHED |
| Object | Kenyapithecus wickeri |
—
|
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: Kenyapithecus wickeri | Statement: [Fort Ternan, fossilsDiscoveredInclude, Kenyapithecus wickeri]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fossilsDiscoveredInclude Context triple: [Fort Ternan, fossilsDiscoveredInclude, Kenyapithecus wickeri]
-
A.
containsFossilsOf
chosen
Indicates that one entity (typically a geological formation, rock, or sample) includes fossil remains or traces belonging to another entity (an organism or taxon).
-
B.
fossilDiscoverer
Indicates the relationship in which an agent is the one who discovered or unearthed a particular fossil.
-
C.
fossilsFoundOn
Indicates that fossils are discovered or located on a particular surface, layer, or object.
-
D.
containsFossilsFrom
Indicates that one entity includes or preserves fossil remains originating from another entity.
-
E.
discoveredAsFossilSite
Indicates that a location was identified and recognized as a site containing fossils.
- 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_69f76e75aa6881909b844d00a3888ee5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:12 p.m.