Triple
T2484547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taxaceae |
E55893
|
entity |
| Predicate | typeGenus |
P5980
|
FINISHED |
| Object | Taxus |
E23812
|
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: Taxus | Statement: [Taxaceae, typeGenus, Taxus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taxus Context triple: [Taxaceae, typeGenus, Taxus]
-
A.
Taxus
chosen
Taxus is a genus of evergreen coniferous trees and shrubs, commonly known as yews, valued for their ornamental use and as a source of the anti-cancer compound paclitaxel.
-
B.
Sciadopitys
Sciadopitys is a unique, ancient conifer genus best known for the Japanese umbrella pine, a slow-growing ornamental tree endemic to Japan.
-
C.
Thuja
Thuja is a genus of evergreen coniferous trees and shrubs commonly known as arborvitae, widely used in ornamental landscaping and hedging.
-
D.
Cryptomeria
Cryptomeria is a genus of large, evergreen coniferous trees native to East Asia, best known for the Japanese cedar widely used in timber and ornamental planting.
-
E.
Pseudolarix
Pseudolarix is a small genus of deciduous coniferous trees, commonly known as golden larches, native to eastern China and valued for their ornamental golden autumn foliage.
- 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_69ab49e670a88190b928e08302381710 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd175f5ac8190870db9c6cb8e45bd |
completed | March 7, 2026, 7:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af1f8c02188190a7cf3e0531a66683 |
completed | March 9, 2026, 7:29 p.m. |
Created at: March 6, 2026, 9:45 p.m.