Triple
T1074876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taxus |
E23812
|
entity |
| Predicate | ediblePart |
P23620
|
FINISHED |
| Object | aril is generally considered non-toxic but seeds are poisonous |
—
|
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: aril is generally considered non-toxic but seeds are poisonous | Statement: [Taxus, ediblePart, aril is generally considered non-toxic but seeds are poisonous]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ediblePart Context triple: [Taxus, ediblePart, aril is generally considered non-toxic but seeds are poisonous]
-
A.
fruitCharacteristic
Indicates that a specified characteristic or property is attributed to a particular fruit.
-
B.
primaryFood
Indicates that one entity serves as the main or most important food source for another entity.
-
C.
seatOfBody
Indicates that one entity serves as the physical location or base where another entity (typically an organization or authority) is situated or headquartered.
-
D.
isLegume
Indicates that something belongs to the group of plants classified as legumes, typically producing seeds in pods and often associated with nitrogen-fixing properties.
-
E.
hasPartIn
Indicates that an entity participates in or plays a role within a larger event, process, or composite entity.
- F. None of above. chosen
Provenance (4 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_69a493f1ddf48190a99d54b00e99f8ce |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b92e480c81909a848b48c196a293 |
completed | March 1, 2026, 10:09 p.m. |
| PD | Predicate disambiguation | batch_69a4b73ba8208190be7f3cef8c18689b |
completed | March 1, 2026, 10:01 p.m. |
| PDg | Predicate description generation | batch_69a4b80f0fb08190a19a50e38ae8f16c |
completed | March 1, 2026, 10:05 p.m. |
Created at: March 1, 2026, 7:42 p.m.