Triple
T12284699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lemon Drop Martini |
E292799
|
entity |
| Predicate | hasPrimaryFlavor |
P90711
|
FINISHED |
| Object | lemon |
—
|
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: lemon | Statement: [Lemon Drop Martini, hasPrimaryFlavor, lemon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryFlavor Context triple: [Lemon Drop Martini, hasPrimaryFlavor, lemon]
-
A.
primaryFlavor
chosen
Indicates the dominant or most characteristic taste associated with an item relative to other possible flavors.
-
B.
hasPrimaryFeature
Indicates that an entity possesses a main or most characteristic feature that defines or distinguishes it.
-
C.
isOfficialFlavorOf
Indicates that one item is formally recognized or designated as an official flavor associated with another entity (such as a brand, product line, or event).
-
D.
hasPrimary
Indicates that one entity is designated as the main or most important instance (the primary) in relation to another entity.
-
E.
hasMainIngredient
Indicates that one entity is the primary or most significant ingredient used to make another entity.
- 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_69d6ab690ad081908c0ed3870ec82d53 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d9261e1570819084bb4fdb44aa6aea |
completed | April 10, 2026, 4:32 p.m. |
| PD | Predicate disambiguation | batch_69d91c4d9a9c8190aeb7beaf9792d8f0 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:52 p.m.