Triple
T12452339
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lipton |
E297560
|
entity |
| Predicate | offersVariety |
P88640
|
FINISHED |
| Object | black tea varieties |
—
|
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: black tea varieties | Statement: [Lipton, offersVariety, black tea varieties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersVariety Context triple: [Lipton, offersVariety, black tea varieties]
-
A.
hasVarietyOf
chosen
Indicates that an entity possesses or offers multiple different types, forms, or versions of something.
-
B.
varietyOf
Indicates that one entity is a specific type, kind, or variant of another, more general entity.
-
C.
hasVarietyOfFlavors
Indicates that one entity offers or contains multiple distinct flavors or taste options.
-
D.
hasServiceVariations
Indicates that a service is offered in multiple distinct versions, options, or configurations that differ in some defined characteristics.
-
E.
hasApproximateNumberOfVarieties
Indicates that an entity is associated with an estimated or non-exact count of different varieties or types.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d95151e7348190a1d4953a8b416a13 |
completed | April 10, 2026, 7:36 p.m. |
| PD | Predicate disambiguation | batch_69d94d3c27a08190a0237200203e476d |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:56 p.m.