Triple
T31943419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Three Shrine Festival |
E815584
|
entity |
| Predicate | mainMikoshiBelongTo |
P89637
|
FINISHED |
| Object | Asakusa Shrine |
E252443
|
NE 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: Asakusa Shrine | Statement: [Three Shrine Festival, mainMikoshiBelongTo, Asakusa Shrine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainMikoshiBelongTo Context triple: [Three Shrine Festival, mainMikoshiBelongTo, Asakusa Shrine]
-
A.
hasMikoshi
chosen
Indicates that an entity possesses, contains, or is associated with a mikoshi (a portable Shinto shrine).
-
B.
namesakeShip
Indicates that one entity is a ship that is named after, or serves as the namesake of, another entity.
-
C.
mainShip
Indicates that one entity serves as the primary or principal ship associated with another entity.
-
D.
所属艦
Indicates a relationship where something belongs to, is assigned to, or is part of a particular ship.
-
E.
hasMidoriNoMadoguchi
Indicates that an entity (typically a train station) is equipped with a "Midori no Madoguchi" staffed ticket office or service counter.
- F. None of above.
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_69f348f42d188190a33fc8d20ec50517 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b2758cec8190b0521eb7f2eccb42 |
completed | May 3, 2026, 2:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3542f88f708190b88cf4e5ba317fe8 |
completed | June 19, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:06 a.m.