Triple
T37061590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 琵琶湖 |
E917336
|
entity |
| Predicate | 関連する文化財 |
P153856
|
FINISHED |
| Object |
竹生島神社
竹生島神社は、琵琶湖に浮かぶ竹生島に鎮座し、弁才天信仰や湖上の絶景で知られる古社です。
|
E2209925
|
NE FINISHED |
How this triple was built (3 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: 竹生島神社 | Statement: [琵琶湖, 関連する文化財, 竹生島神社]
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: 竹生島神社 Triple: [琵琶湖, 関連する文化財, 竹生島神社]
Generated description
竹生島神社は、琵琶湖に浮かぶ竹生島に鎮座し、弁才天信仰や湖上の絶景で知られる古社です。
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 関連する文化財 Context triple: [琵琶湖, 関連する文化財, 竹生島神社]
-
A.
culturalProperty
Indicates that something is recognized or treated as a cultural property, typically denoting legal or heritage status tied to cultural significance.
-
B.
関連する作品
Indicates that one work is related to another work, such as by theme, series, adaptation, or other contextual connection.
-
C.
relationshipToNationalTreasures
Indicates a specified type of connection or association that an entity has with designated national treasures.
-
D.
hasCulturalHeritageLink
chosen
Indicates a relationship where one entity is culturally derived from, influenced by, or historically connected to another.
-
E.
نوع_آثار_مرتبط
Indicates a relationship where one entity is associated with another through a specific type or category of related works or artifacts.
- F. None of above.
Provenance (6 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_69f76e95fa40819091e14681087ae5e4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb55de3b9c8190a7656aeab3c3ffbc |
completed | May 6, 2026, 2:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3e8c5715e8819082c99d589abd3baa |
completed | June 26, 2026, 2:27 p.m. |
| NEDg | Description generation | batch_6a3e95ede37c8190976559fecd7917b3 |
completed | June 26, 2026, 3:08 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a3e9914a3e48190bf59606bacf80c87 |
completed | June 26, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69fb35bc92e08190bff447624e2df791 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:14 p.m.