Triple
T15725813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japanese traditional calendar |
E381214
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Higan
Higan is a Japanese Buddhist observance held around the spring and autumn equinoxes, marked by visits to family graves and reflection on spiritual balance.
|
E1173659
|
NE FINISHED |
How this triple was built (4 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: Higan | Statement: [Japanese traditional calendar, hasPart, Higan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Higan Context triple: [Japanese traditional calendar, hasPart, Higan]
-
A.
Sendagaya
Sendagaya is a neighborhood in Tokyo known for its sports facilities, including the National Stadium, and its proximity to Shinjuku and Harajuku.
-
B.
Shichahai
Shichahai is a historic scenic area in central Beijing known for its interconnected lakes, traditional hutong neighborhoods, and vibrant cultural and leisure activities.
-
C.
Higashi
Higashi is a residential and commercial neighborhood located in Tokyo's Shibuya ward.
-
D.
Gyōkyō
Gyōkyō was a Buddhist monk traditionally credited with establishing the important Shinto-Buddhist shrine Iwashimizu Hachimangū in Japan.
-
E.
Kakurinji
Kakurinji is a historic Buddhist temple in Japan, best known as Temple 20 on the Shikoku Pilgrimage route.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Higan Triple: [Japanese traditional calendar, hasPart, Higan]
Generated description
Higan is a Japanese Buddhist observance held around the spring and autumn equinoxes, marked by visits to family graves and reflection on spiritual balance.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Higan Target entity description: Higan is a Japanese Buddhist observance held around the spring and autumn equinoxes, marked by visits to family graves and reflection on spiritual balance.
-
A.
Sendagaya
Sendagaya is a neighborhood in Tokyo known for its sports facilities, including the National Stadium, and its proximity to Shinjuku and Harajuku.
-
B.
Shichahai
Shichahai is a historic scenic area in central Beijing known for its interconnected lakes, traditional hutong neighborhoods, and vibrant cultural and leisure activities.
-
C.
Higashi
Higashi is a residential and commercial neighborhood located in Tokyo's Shibuya ward.
-
D.
Gyōkyō
Gyōkyō was a Buddhist monk traditionally credited with establishing the important Shinto-Buddhist shrine Iwashimizu Hachimangū in Japan.
-
E.
Kakurinji
Kakurinji is a historic Buddhist temple in Japan, best known as Temple 20 on the Shikoku Pilgrimage route.
- F. None of above. chosen
Provenance (5 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_69d86d9cdb648190bf3171be0bd7d872 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04fb357a88190a92641c8a8c20573 |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff82f8b88081909855d3da0346fa25 |
completed | May 9, 2026, 6:54 p.m. |
| NEDg | Description generation | batch_69ff83e73efc8190bf29248346d61af5 |
completed | May 9, 2026, 6:58 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff8477b94081909814d0672dd7052f |
completed | May 9, 2026, 7:01 p.m. |
Created at: April 10, 2026, 4:46 a.m.