Triple
T3774333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rousselia |
E83271
|
entity |
| Predicate | hasSpecies |
P965
|
FINISHED |
| Object | Rousselia media |
E83271
|
NE 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: Rousselia media | Statement: [Rousselia, hasSpecies, Rousselia media]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rousselia media Context triple: [Rousselia, hasSpecies, Rousselia media]
-
A.
Rousselia
chosen
Rousselia is a genus of flowering plants in the hemp family Cannabaceae, native to tropical regions of the Americas.
-
B.
Reissekia
Reissekia is a small genus of flowering plants in the buckthorn family Rhamnaceae, native to parts of South America.
-
C.
Fragosphaeria
Fragosphaeria is a genus of fungi classified within the family Ophiostomataceae, which comprises species often associated with wood and bark.
-
D.
Vibrionales
Vibrionales is an order of Gram-negative, mostly aquatic bacteria that includes several pathogenic species, notably those causing cholera and other gastrointestinal diseases.
-
E.
Latreillea
Latreillea is a taxonomic genus named in honor of the French entomologist Pierre André Latreille.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad8b235e608190b5a2b1d1bfcef50b |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc594c50819099ab5ac1b82f61a6 |
completed | March 8, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b503ea77708190ae55cd1892735b22 |
completed | March 14, 2026, 6:44 a.m. |
Created at: March 8, 2026, 3:36 p.m.