Triple
T25327047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shrikhand |
E635045
|
entity |
| Predicate | typicalAdditive |
P12230
|
FINISHED |
| Object | chopped nuts |
—
|
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: chopped nuts | Statement: [Shrikhand, typicalAdditive, chopped nuts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalAdditive Context triple: [Shrikhand, typicalAdditive, chopped nuts]
-
A.
typicalIn
chosen
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
B.
typicalExponent
Indicates that one quantity serves as the characteristic or standard exponent associated with another quantity or expression.
-
C.
typicalBoost
Indicates a standard or commonly expected increase in magnitude, intensity, or effectiveness associated with something.
-
D.
typicalBase
Indicates that one entity serves as the standard or most representative base or foundation for another entity in typical or common cases.
-
E.
typicalOption
Indicates that one option is considered standard, common, or most representative among a set of possible options.
- 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_69e75a9908108190a95427a97020632a |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69fcf36d2894819089b7db8e91b63c9d |
completed | May 7, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69fcf25c0a108190bfa823474098640b |
completed | May 7, 2026, 8:13 p.m. |
Created at: April 21, 2026, 1:30 p.m.