Triple
T3812540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kyushu Shinkansen |
E93167
|
entity |
| Predicate | initialSectionOpeningDate |
P10845
|
FINISHED |
| Object | 2004-03-13 |
—
|
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: 2004-03-13 | Statement: [Kyushu Shinkansen, initialSectionOpeningDate, 2004-03-13]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialSectionOpeningDate Context triple: [Kyushu Shinkansen, initialSectionOpeningDate, 2004-03-13]
-
A.
firstLineOpeningDate
Indicates the date on which the first line in a system, network, or service was officially opened or began operation.
-
B.
officialOpeningDate
chosen
Indicates the calendar date on which something is formally inaugurated or officially opened for use or operation.
-
C.
openedAt
Indicates that an entity began operating, became accessible, or was first made available at a specific time or date.
-
D.
firstOpenedAt
Indicates the date and time at which something was initially opened for the first time.
-
E.
softOpeningDate
Indicates the date on which a business, venue, or service begins limited or trial operations before its official grand opening.
- 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_69aed96a60088190ab1df8390fffc935 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aef1515c688190a38332aedeed8a76 |
completed | March 9, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_69aee7482d708190a3ec74745b102a4c |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:16 p.m.