Triple
T7265706
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 0 Series Shinkansen |
E159767
|
entity |
| Predicate | retiredFromRegularService |
P35163
|
FINISHED |
| Object | 2000 |
—
|
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: 2000 | Statement: [0 Series Shinkansen, retiredFromRegularService, 2000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: retiredFromRegularService Context triple: [0 Series Shinkansen, retiredFromRegularService, 2000]
-
A.
retiredFrom
Indicates that an entity has permanently stopped working for or being active in a specified organization, role, or activity.
-
B.
retiredFromFrontlineService
chosen
Indicates that an entity has ceased active, primary operational duties and is no longer serving in a frontline role.
-
C.
retiredFromIcebreakingService
Indicates that an entity has ceased performing icebreaking operations and is no longer in active icebreaking service.
-
D.
retiredTo
Indicates that an entity has permanently left active service or work and taken up residence or status in a particular place or role as their retirement destination.
-
E.
retiredBy
Indicates that one entity has formally ended the active status, use, or service of another entity.
- 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_69c68838f9948190875fd60b2351230c |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb088dac8190b353f6ea3d686025 |
completed | March 27, 2026, 8:39 p.m. |
| PD | Predicate disambiguation | batch_69c6e76876608190ac4652bc7153302e |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:57 p.m.