Triple
T27742403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nankai Limited Express Rapi:t |
E701889
|
entity |
| Predicate | openingRelatedEvent |
P77470
|
FINISHED |
| Object | opening of Kansai International Airport |
—
|
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: opening of Kansai International Airport | Statement: [Nankai Limited Express Rapi:t, openingRelatedEvent, opening of Kansai International Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openingRelatedEvent Context triple: [Nankai Limited Express Rapi:t, openingRelatedEvent, opening of Kansai International Airport]
-
A.
openingRelatedTo
chosen
Indicates a relationship where one entity’s opening (such as a beginning, introduction, or initial part) is connected or relevant to another entity.
-
B.
openedForEvent
Indicates that a venue or location is made accessible and operational specifically for a particular event.
-
C.
openingTo
Indicates that one entity serves as an entrance, access point, or passage leading into or toward another entity.
-
D.
openingBegan
Indicates that the process of opening something has started.
-
E.
openingDynamic
Indicates that one entity initiates or begins another entity or process in a way that can change or vary over time or context.
- 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_69ef6a53c7388190899baa6daf42301c |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 27, 2026, 4:12 p.m.