Triple
T30317022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanabata |
E771084
|
entity |
| Predicate | usesDecoration |
P38145
|
FINISHED |
| Object | tanzaku |
—
|
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: tanzaku | Statement: [Tanabata, usesDecoration, tanzaku]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesDecoration Context triple: [Tanabata, usesDecoration, tanzaku]
-
A.
hasDecor
chosen
Indicates that one entity possesses, features, or is adorned with a particular decorative element or style.
-
B.
containsDecorationFrom
Indicates that one entity includes or incorporates a decorative element that originates from another entity.
-
C.
usesTraditionalDecoration
Indicates that an entity employs customary or historically established decorative styles or motifs in its design or presentation.
-
D.
relatedDecoration
Indicates that one decoration is associated with, complements, or is contextually linked to another decoration.
-
E.
valorDecoration
Indicates that an entity has been awarded a decoration or honor specifically in recognition of acts of valor or bravery.
- 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_69f22488f224819081b0f3ec41ab975c |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca3dedc81908b519d53d2909868 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 29, 2026, 7:51 p.m.