Triple
T34744407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tsing Sha Highway |
E1001594
|
entity |
| Predicate | formsTransportLinkTo |
P70574
|
FINISHED |
| Object | Hong Kong International Airport |
—
|
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: Hong Kong International Airport | Statement: [Tsing Sha Highway, formsTransportLinkTo, Hong Kong International Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsTransportLinkTo Context triple: [Tsing Sha Highway, formsTransportLinkTo, Hong Kong International Airport]
-
A.
transportLinkType
Indicates the specific kind of transportation connection or route that exists between two locations or transport nodes.
-
B.
formsTransportCorridorBetween
chosen
Indicates that something creates or constitutes a transportation link or route connecting two locations or entities.
-
C.
transportFrom
Indicates that something or someone is moved or carried away starting from a specified origin location.
-
D.
transportConnectionTo
Indicates a relationship where one entity provides or participates in a means of transportation that connects or leads to another entity.
-
E.
replacedTransportLink
Indicates that one transport connection has been superseded or substituted by another transport connection.
- 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_69f76db0367081909b57c50a7fb03025 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fd0b92f42881908cd77e3f058adcc2 |
completed | May 7, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fd0a3d68d4819094d92040f7c48d7c |
completed | May 7, 2026, 9:55 p.m. |
Created at: May 3, 2026, 3:59 p.m.