Triple
T16513675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lu’an Guapian tea |
E401125
|
entity |
| Predicate | leafProcessingFeature |
P29126
|
FINISHED |
| Object | made from tea leaves without buds |
—
|
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: made from tea leaves without buds | Statement: [Lu’an Guapian tea, leafProcessingFeature, made from tea leaves without buds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leafProcessingFeature Context triple: [Lu’an Guapian tea, leafProcessingFeature, made from tea leaves without buds]
-
A.
spanFeature
Indicates a relationship where a feature or characteristic extends across or covers a specified span or interval.
-
B.
leafType
Indicates the specific kind or classification of leaf associated with an entity.
-
C.
leafProperty
Indicates that the subject has a property that is terminal (i.e., not further decomposed into sub-properties) within a property hierarchy or structure.
-
D.
processFeature
chosen
Indicates that an entity performs or undergoes an operation that handles, transforms, or otherwise acts upon a specific feature.
-
E.
leafPosition
Indicates the spatial or structural placement of a leaf relative to its supporting plant organ or axis.
- 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_69d88381f6148190819958a038be990e |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e78d4848190a55de9902115b1b2 |
completed | April 18, 2026, 7:10 a.m. |
| PD | Predicate disambiguation | batch_69e296995d388190b88ebe189dce890d |
completed | April 17, 2026, 8:22 p.m. |
Created at: April 10, 2026, 5:14 a.m.