Triple
T29737662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | G3 Beijing–Taipei Expressway |
E752507
|
entity |
| Predicate | plannedConnection |
P82020
|
FINISHED |
| Object | Taiwan via a cross-strait link |
—
|
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: Taiwan via a cross-strait link | Statement: [G3 Beijing–Taipei Expressway, plannedConnection, Taiwan via a cross-strait link]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plannedConnection Context triple: [G3 Beijing–Taipei Expressway, plannedConnection, Taiwan via a cross-strait link]
-
A.
plannedToConnectCity
Indicates that an entity had the intention or made arrangements to establish a connection or link between cities.
-
B.
plannedVia
chosen
Indicates that something is arranged, organized, or scheduled by means of a particular method, process, or intermediary.
-
C.
plannedWith
Indicates that an entity created or arranged a plan in collaboration or coordination with another entity.
-
D.
connectionTo
Indicates a relationship in which one entity is linked, associated, or otherwise related to another entity.
-
E.
plannedIn
Indicates that an event, activity, or process is scheduled or arranged to occur within a specific context, timeframe, or plan.
- 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_69f0d62a36a88190bf860f00da433ff8 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f74062b9388190b30546cf700a825c |
completed | May 3, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69f73c802b848190b61a416b7488bd96 |
completed | May 3, 2026, 12:16 p.m. |
Created at: April 28, 2026, 7:46 p.m.