Triple
T13763318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 500 series Shinkansen |
E330669
|
entity |
| Predicate | tilting |
P64479
|
FINISHED |
| Object | no active tilting |
—
|
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: no active tilting | Statement: [500 series Shinkansen, tilting, no active tilting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tilting Context triple: [500 series Shinkansen, tilting, no active tilting]
-
A.
tiltingCapability
Indicates the ability of one entity to tilt or be tilted relative to another or to a reference orientation.
-
B.
tiltingMechanism
chosen
Indicates a relationship where one entity serves as a mechanism that enables another entity to tilt or be tilted.
-
C.
tiltedRelativeTo
Indicates that one entity is oriented at an angle with respect to another, rather than being parallel or perpendicular.
-
D.
tiltingSubClass
Indicates that one class is a specialized tilting-related subclass or refinement of another class within a hierarchical relationship.
-
E.
turns
Indicates a change in orientation, direction, or state initiated by one entity affecting itself or 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_69d81c583b0081909e408a17db517a21 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de022690ac8190bd5410ecc659a2a7 |
completed | April 14, 2026, 9 a.m. |
| PD | Predicate disambiguation | batch_69dbbe97846c819093b00ea117b64e0d |
completed | April 12, 2026, 3:47 p.m. |
Created at: April 9, 2026, 10:10 p.m.