Triple
T13281699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maizuru |
E316336
|
entity |
| Predicate | hasAttraction |
P105
|
FINISHED |
| Object | Maizuru Park |
E864348
|
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: Maizuru Park | Statement: [Maizuru, hasAttraction, Maizuru Park]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maizuru Park Context triple: [Maizuru, hasAttraction, Maizuru Park]
-
A.
Maizuru Park
chosen
Maizuru Park is a historic public park in Fukuoka, Japan, known for its cherry blossoms and the ruins of Fukuoka Castle.
-
B.
Mizumoto Park
Mizumoto Park is a large riverside public park in Tokyo known for its expansive greenery, ponds, and popular iris garden.
-
C.
Ōmiya Park
Ōmiya Park is a large public park in Saitama, Japan, known for its cherry blossoms, sports facilities, and the Hikawa Shrine.
-
D.
Okubo Park
Okubo Park is a public urban park located in the Ōkubo district of Shinjuku, Tokyo, known as a local green space amid the dense cityscape.
-
E.
Nakajima Park
Nakajima Park is a large, scenic urban park in central Sapporo known for its ponds, walking paths, cultural facilities, and seasonal beauty.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d806b349908190a9a61dd9323bf153 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9904507588190a303686d176ec3e1 |
completed | April 11, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7305e1d70819096ff9784e9fafde9 |
completed | May 3, 2026, 11:24 a.m. |
Created at: April 9, 2026, 9:27 p.m.