Triple
T25896796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shenzhen Stock Exchange building |
E652486
|
entity |
| Predicate | hasTradingFloorLocation |
P5156
|
FINISHED |
| Object | elevated podium volume |
—
|
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: elevated podium volume | Statement: [Shenzhen Stock Exchange building, hasTradingFloorLocation, elevated podium volume]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTradingFloorLocation Context triple: [Shenzhen Stock Exchange building, hasTradingFloorLocation, elevated podium volume]
-
A.
hasTradingFloorFor
Indicates that one entity operates or provides a trading floor facility used for conducting trading activities related to another entity.
-
B.
hasTradingFloor
chosen
Indicates that an entity operates or contains a physical or virtual trading floor where financial instruments are actively bought and sold.
-
C.
hasTradingVenueCode
Indicates that an entity is associated with a specific trading venue through its designated code.
-
D.
hasTradingVenueType
Indicates the specific category or type of trading venue associated with a given trading platform or marketplace.
-
E.
hasStoreLocation
Indicates that an entity operates or maintains a store at a specified physical location.
- 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_69e7ab3c6cc081908de59bfcc28ec19d |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 22, 2026, 8:23 a.m.