Triple
T2699215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hong Kong–Zhuhai–Macau Bridge |
E58588
|
entity |
| Predicate | underseaTunnelLength |
P19266
|
FINISHED |
| Object | about 6.7 kilometers |
—
|
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: about 6.7 kilometers | Statement: [Hong Kong–Zhuhai–Macau Bridge, underseaTunnelLength, about 6.7 kilometers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underseaTunnelLength Context triple: [Hong Kong–Zhuhai–Macau Bridge, underseaTunnelLength, about 6.7 kilometers]
-
A.
SeikanTunnelConnects
Indicates that the Seikan Tunnel serves as a physical connection between two geographic locations or regions.
-
B.
hasSubseaTunnel
Indicates that one location or structure is connected to another by an underwater tunnel.
-
C.
SeikanTunnelType
Indicates that one entity is classified as a specific type or category of Seikan Tunnel.
-
D.
lengthUnderseaSection
chosen
Indicates that the specified length pertains to the portion of an object or route that lies beneath the sea surface.
-
E.
hasBridgeTunnel
Indicates that there exists a bridge or tunnel connection between two locations or structures.
- 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_69ab4ac269e481909cb317d79e68b75b |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda339cf48190b9ae6b99137f005e |
completed | March 7, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69abd82062988190b4292f242ad70b2c |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.