Triple
T479103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aji de gallina |
E9125
|
entity |
| Predicate | keySpice |
P5688
|
FINISHED |
| Object | ají amarillo pepper |
—
|
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: ají amarillo pepper | Statement: [Aji de gallina, keySpice, ají amarillo pepper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keySpice Context triple: [Aji de gallina, keySpice, ají amarillo pepper]
-
A.
key
Indicates that one entity functions as a key (literal or metaphorical) that unlocks, enables access to, or provides a crucial solution or control over another entity.
-
B.
keyComponent
chosen
Indicates that one entity is an essential or foundational part required for the proper function, structure, or identity of another entity.
-
C.
keyFeature
Indicates that something is a primary, distinguishing, or most important feature of an entity.
-
D.
keySymbol
Indicates that one entity serves as the symbolic representation or notation used to denote another entity as a key.
-
E.
keyExperiment
Indicates that an experiment plays a central or pivotal role within a broader study, project, or research context.
- 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_69a2e7ff81708190b0507a24a997232c |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2f056459881909749764cc4a7f9e8 |
completed | Feb. 28, 2026, 1:40 p.m. |
| PD | Predicate disambiguation | batch_69a2edf1d5848190a7da27e2fddc136f |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.