Triple
T27199474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sannō Matsuri |
E683695
|
entity |
| Predicate | cityCelebrated |
P2151
|
FINISHED |
| Object | Tokyo |
—
|
NE NERFINISHED |
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: Tokyo | Statement: [Sannō Matsuri, cityCelebrated, Tokyo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cityCelebrated Context triple: [Sannō Matsuri, cityCelebrated, Tokyo]
-
A.
mainCityCelebrations
chosen
Indicates that major celebratory events or festivities are held in or associated with a particular main city.
-
B.
celebratedEvent
Indicates that an entity has been honored, commemorated, or festively observed as a special event.
-
C.
celebratedThrough
Indicates that something is honored, recognized, or observed by means of a particular activity, medium, or practice.
-
D.
capitalOfCelebration
Indicates that a location is recognized as the primary or central place where a particular celebration or festivity is most prominently held or symbolically based.
-
E.
celebratedEvery
Indicates that an event, occasion, or action is celebrated on a recurring basis at every specified time interval or condition.
- 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_69eefad1fd5c8190a4a46ea6afe58bfa |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f625dea3788190a97467cc8e613a12 |
completed | May 2, 2026, 4:27 p.m. |
| PD | Predicate disambiguation | batch_69f620e38aec8190bb184edcdbd6da64 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 9:35 a.m.