Triple
T19925481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pinduoduo |
E478910
|
entity |
| Predicate | userAcquisitionChannel |
P71475
|
FINISHED |
| Object | WeChat social sharing |
—
|
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: WeChat social sharing | Statement: [Pinduoduo, userAcquisitionChannel, WeChat social sharing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: userAcquisitionChannel Context triple: [Pinduoduo, userAcquisitionChannel, WeChat social sharing]
-
A.
ownedChannel
Indicates that one entity possesses ownership or control over a particular channel.
-
B.
availabilityChannel
chosen
Indicates the medium or channel through which something (such as a product, service, or resource) is made available or can be accessed.
-
C.
registrationChannel
Indicates the method or medium through which a registration was initiated or completed between entities.
-
D.
licensingChannel
Indicates the medium or route through which a license is obtained, distributed, or managed between parties.
-
E.
formsNaturalChannelFor
Indicates that one entity naturally shapes or provides a passage or conduit through which another entity (such as a fluid, material, or flow) can move or be directed.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659c992fc8190bd262d528be0e636 |
completed | April 20, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69e537f070b481908958e0e5911dcdc1 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:53 p.m.