Triple
T37039900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roppongi Keyakizaka-dori |
E916749
|
entity |
| Predicate | illuminationTheme |
P187270
|
FINISHED |
| Object | view of Tokyo Tower framed by lights |
—
|
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: view of Tokyo Tower framed by lights | Statement: [Roppongi Keyakizaka-dori, illuminationTheme, view of Tokyo Tower framed by lights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: illuminationTheme Context triple: [Roppongi Keyakizaka-dori, illuminationTheme, view of Tokyo Tower framed by lights]
-
A.
illuminationSeason
Indicates the season or time of year during which something is illuminated or lit.
-
B.
illuminationMedium
Indicates the medium or method through which illumination or light is produced or delivered in a given context.
-
C.
illuminationCondition
Indicates the lighting or brightness conditions under which an event, observation, or interaction takes place.
-
D.
illuminationPurpose
Indicates that one entity serves the purpose of providing light or illumination for another entity or context.
-
E.
themeInArc
Indicates that something serves as a central theme or recurring subject within a particular narrative arc.
- F. None of above. chosen
Provenance (4 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_69f76e93ec4c8190be81cf87354d9155 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb34e5576881909394355c8ec6ddd2 |
completed | May 6, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69fb2f6171e88190bf1e0ee6a644b6a9 |
completed | May 6, 2026, 12:09 p.m. |
| PDg | Predicate description generation | batch_69fb34e4906c8190abb1c293fb84329a |
completed | May 6, 2026, 12:32 p.m. |
Created at: May 3, 2026, 4:14 p.m.