Triple
T26551428
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 福岡県太宰府市 |
E671686
|
entity |
| Predicate | 関連する防衛施設 |
P114533
|
FINISHED |
| Object |
水城
水城は、福岡県太宰府市周辺で大宰府を外敵から守るために7世紀に築かれた古代山城式の防衛施設・土塁です。
|
E1733286
|
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: 水城 | Statement: [福岡県太宰府市, 関連する防衛施設, 水城]
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: 水城 Triple: [福岡県太宰府市, 関連する防衛施設, 水城]
Generated description
水城は、福岡県太宰府市周辺で大宰府を外敵から守るために7世紀に築かれた古代山城式の防衛施設・土塁です。
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 関連する防衛施設 Context triple: [福岡県太宰府市, 関連する防衛施設, 水城]
-
A.
関連施設
Indicates a relationship where one facility is associated with, connected to, or otherwise related to another facility.
-
B.
関連城郭
Indicates a relationship where something is associated with or related to a particular castle or fortification.
-
C.
shareDefenseStructure
chosen
Indicates that two or more entities utilize or are protected by the same defensive structure or system.
-
D.
relatedInfrastructure
Indicates that one piece of infrastructure is connected, associated, or functionally related to another infrastructure element.
-
E.
nearMilitaryInstallation
Indicates that one entity is located in close physical proximity to a military installation or facility.
- 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_69eeb32163f08190af5f81282738e27a |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f614624c80819084f6febf57f86828 |
completed | May 2, 2026, 3:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a11c81e26288190b027a84873d72943 |
completed | May 23, 2026, 3:30 p.m. |
| NEDg | Description generation | batch_6a11e5247fe88190bcd9a7afe016f3a2 |
completed | May 23, 2026, 5:34 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a11e5f0744c8190904d781ba9d7e28c |
completed | May 23, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69f602d7b1b0819095ddd3b5169f8ce2 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 27, 2026, 1:47 a.m.