Triple
T1548600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | China Southern Airlines |
E33034
|
entity |
| Predicate | stockExchangeTicker |
P1447
|
FINISHED |
| Object | 600029 |
—
|
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: 600029 | Statement: [China Southern Airlines, stockExchangeTicker, 600029]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stockExchangeTicker Context triple: [China Southern Airlines, stockExchangeTicker, 600029]
-
A.
tickerSymbol
chosen
Indicates the association between a financial instrument or company and its unique abbreviated code used for trading on a securities exchange.
-
B.
stockIndex
Indicates a relationship where a stock market index tracks or represents the aggregated performance of a selected group of stocks.
-
C.
hasStockExchange
Indicates that an entity is associated with or listed on a particular stock exchange.
-
D.
tradedOn
Indicates that an asset, security, or instrument is bought and sold on a particular exchange or trading venue.
-
E.
isExchangeTraded
Indicates that the entity is traded on a formal exchange or marketplace rather than over-the-counter or privately.
- 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_69a885ee6db8819099502bc5ce8af881 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa574094048190a2d7fc3ac904d51e |
completed | March 6, 2026, 4:25 a.m. |
| PD | Predicate disambiguation | batch_69a907b426dc8190975c024a50955368 |
completed | March 5, 2026, 4:33 a.m. |
Created at: March 4, 2026, 7:26 p.m.