Triple
T13959390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ficus carica |
E335750
|
entity |
| Predicate | latexProduction |
P21055
|
FINISHED |
| Object | produces milky latex in stems and leaves |
—
|
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: produces milky latex in stems and leaves | Statement: [Ficus carica, latexProduction, produces milky latex in stems and leaves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: latexProduction Context triple: [Ficus carica, latexProduction, produces milky latex in stems and leaves]
-
A.
latexType
Indicates that one entity specifies or classifies the LaTeX formatting or representation type associated with another entity.
-
B.
hasLatex
chosen
Indicates that one entity possesses, contains, or is associated with latex in relation to another entity.
-
C.
documentTypeProduced
Indicates that one entity produces, generates, or creates a document of a specified type.
-
D.
paper2Type
Indicates that a given paper is associated with, or classified as, a specific type or category of paper.
-
E.
latexEffect
Indicates that one entity has an effect on another involving latex, such as application, influence, or transformation through latex material or properties.
- 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_69d81c61f3508190aaf2ca0dc0002c59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e7b2f908190aa32f22298964746 |
completed | April 14, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69de05a3ccf88190b45c742db483fa08 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:17 p.m.