Triple
T25424990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | China Eastern Airlines |
E637094
|
entity |
| Predicate | headquartersAirportRegion |
P5413
|
FINISHED |
| Object | Yangtze River Delta |
—
|
NE NERFINISHED |
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: Yangtze River Delta | Statement: [China Eastern Airlines, headquartersAirportRegion, Yangtze River Delta]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: headquartersAirportRegion Context triple: [China Eastern Airlines, headquartersAirportRegion, Yangtze River Delta]
-
A.
hasRegionalAirport
Indicates that a place or region possesses or is served by a regional airport.
-
B.
isMajorRegionalAirportFor
Indicates that an airport serves as a primary or significant air travel hub for a particular region.
-
C.
headquartersMetroArea
chosen
Indicates that an organization’s main headquarters is located within a specified metropolitan area.
-
D.
isRegionalAirport
Indicates that an airport serves a specific region or local area rather than functioning as a major national or international hub.
-
E.
operatorHeadquartersAirport
Indicates that the specified airport serves as the primary headquarters location for the operator.
- 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_69e75db58a1c8190891b9ff7c2f8414e |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f6bf25c881909f049d5393927bfb |
completed | May 2, 2026, 1:06 p.m. |
| PD | Predicate disambiguation | batch_69f45d0dbc8c8190beecce679fce90a4 |
completed | May 1, 2026, 7:58 a.m. |
Created at: April 21, 2026, 1:57 p.m.