Triple
T5350510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas's leaf monkey |
E124165
|
entity |
| Predicate | digestiveType |
P58139
|
FINISHED |
| Object | foregut fermenter |
—
|
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: foregut fermenter | Statement: [Thomas's leaf monkey, digestiveType, foregut fermenter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: digestiveType Context triple: [Thomas's leaf monkey, digestiveType, foregut fermenter]
-
A.
digestiveMethod
Indicates the way or process by which an entity digests or breaks down food or nutrients.
-
B.
stomachType
Indicates the kind or classification of stomach an entity has, typically describing its structural or functional type.
-
C.
digestiveSystem
Indicates the relationship in which an entity possesses or is associated with a system responsible for breaking down food and absorbing nutrients.
-
D.
gutType
chosen
Indicates the type or classification of a digestive tract or gut associated with an entity.
-
E.
hasStomachType
Indicates that an entity possesses or is characterized by a specific type or classification of stomach.
- 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_69bd464be27081908807b40b75c1bbae |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd860fe4048190846a933d0e1b9386 |
completed | March 20, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69bd845c6f108190832a8d14b356368a |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:01 p.m.