Triple
T16120362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Li Auto |
E391117
|
entity |
| Predicate | hasShowroomsIn |
P26597
|
FINISHED |
| Object | multiple Chinese cities |
—
|
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: multiple Chinese cities | Statement: [Li Auto, hasShowroomsIn, multiple Chinese cities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasShowroomsIn Context triple: [Li Auto, hasShowroomsIn, multiple Chinese cities]
-
A.
hasRetailPresenceIn
chosen
Indicates that an entity conducts retail operations or maintains a retail outlet, store, or sales presence within a specified location.
-
B.
hasRetailBoutiquesIn
Indicates that an entity operates or maintains retail boutiques located within a specified place or region.
-
C.
hasRentalShop
Indicates that one entity operates, owns, or is associated with a rental shop used to provide items or services for rent to others.
-
D.
hasShopsOn
Indicates that one entity (typically a street, area, or building) contains or is lined with shops located on or along it.
-
E.
storefront
Indicates the physical or virtual front-facing location where a business presents and offers its goods or services to customers.
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e20200acac8190a47e6a917ff8dd34 |
completed | April 17, 2026, 9:48 a.m. |
| PD | Predicate disambiguation | batch_69e1828518c48190a8ef3aaa46a1f639 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5 a.m.