Triple
T8103955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghai Metro Line 2 |
E189179
|
entity |
| Predicate | connectsBothAirports |
P23780
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Shanghai Metro Line 2, connectsBothAirports, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsBothAirports Context triple: [Shanghai Metro Line 2, connectsBothAirports, true]
-
A.
connectsWithAirport
chosen
Indicates that there is a direct transportation or operational link established between an entity and an airport.
-
B.
hasAirsideConnection
Indicates that there is a direct, secure connection between areas past security (airside) of two locations, allowing passengers to transfer without re-clearing security or immigration.
-
C.
sharesAirportWith
Indicates that two entities use or are associated with the same airport.
-
D.
hasLandsideConnection
Indicates that two locations are connected by a route or access on land, allowing movement between them without using air or water transport.
-
E.
hasCityPair
Indicates a relationship that links two cities considered as a connected or associated pair, often for purposes such as travel, trade, or comparison.
- 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_69ca82b9d5848190a24672775d5c5011 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb42bf1cb0819099dda4f050f8e95e |
completed | March 31, 2026, 3:42 a.m. |
| PD | Predicate disambiguation | batch_69cb04a2ed1c8190b73562321ad688bc |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:31 p.m.