Triple
T36895128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Casablanca |
E911869
|
entity |
| Predicate | wineFocus |
P2082
|
FINISHED |
| Object | white wines |
—
|
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: white wines | Statement: [Casablanca, wineFocus, white wines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wineFocus Context triple: [Casablanca, wineFocus, white wines]
-
A.
wineList
Indicates that an entity is a list or collection of wines associated with another entity (such as a restaurant, event, or menu).
-
B.
wineStyle
chosen
Indicates the stylistic category or type of wine (such as its production style, sweetness, body, or other defining characteristics) associated with an entity.
-
C.
wineCategory
Indicates the classification or type of wine that an entity (such as a specific wine) belongs to.
-
D.
wineCountry
Indicates that a location is recognized as a region where wine is produced, typically known for its vineyards and wineries.
-
E.
notableWine
Indicates that a wine is recognized as significant, distinguished, or noteworthy in some context (such as quality, reputation, or historical importance).
- 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_69f76e841b54819097e7fa768bbc70b2 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd8d3ad08190854b227055102a89 |
completed | May 5, 2026, 2:24 p.m. |
| PD | Predicate disambiguation | batch_69f7cf79ddb08190a083405cccc14137 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.