Triple
T31257870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shui Xian |
E797029
|
entity |
| Predicate | teaTypeComparison |
P171509
|
FINISHED |
| Object | heavier roast than Tie Guan Yin |
—
|
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: heavier roast than Tie Guan Yin | Statement: [Shui Xian, teaTypeComparison, heavier roast than Tie Guan Yin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teaTypeComparison Context triple: [Shui Xian, teaTypeComparison, heavier roast than Tie Guan Yin]
-
A.
teaType
Indicates the specific variety or category of tea associated with an entity.
-
B.
teaCategory
Indicates that one item is classified as belonging to a particular category or type of tea.
-
C.
hasTeeType
Indicates that an entity (typically a golf hole or course) is associated with a specific type or category of tee.
-
D.
teaBrand
Indicates that one entity is a brand or producer associated with a particular type or product line of tea for the other entity.
-
E.
teaProduct
Indicates that something is a product related to tea, such as an item made from, flavored with, or intended for preparing or consuming tea.
- F. None of above. chosen
Provenance (4 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_69f224dd5fdc81908a4cd24917b67668 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69f80b62c8190bf2af2be0d3a7df8 |
completed | May 3, 2026, 1:06 a.m. |
| PD | Predicate disambiguation | batch_69f69d1bf8cc8190a78dfa5ab00daf3a |
completed | May 3, 2026, 12:55 a.m. |
| PDg | Predicate description generation | batch_69f69edae2448190925ce701c8792c52 |
completed | May 3, 2026, 1:03 a.m. |
Created at: April 29, 2026, 9:12 p.m.