Triple
T12240080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yasukuni Shrine |
E291705
|
entity |
| Predicate | formerName |
P65
|
FINISHED |
| Object |
Tokyo Shokonsha
Tokyo Shokonsha was the original name of what is now Yasukuni Shrine, a Shinto shrine in Tokyo dedicated to commemorating Japan’s war dead.
|
E970967
|
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: Tokyo Shokonsha | Statement: [Yasukuni Shrine, formerName, Tokyo Shokonsha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tokyo Shokonsha Context triple: [Yasukuni Shrine, formerName, Tokyo Shokonsha]
-
A.
Kodansha
Kodansha is a major Japanese publishing company best known for producing and distributing popular manga, novels, and magazines worldwide.
-
B.
Chūō Kōron Shinsha
Chūō Kōron Shinsha is a major Japanese publishing company known for its influential literary and cultural magazines and books.
-
C.
Shueisha
Shueisha is a major Japanese publishing company best known for producing popular manga magazines such as Weekly Shōnen Jump.
-
D.
Bunko-dō publishing house
Bunko-dō publishing house was a Japanese publisher known for its association with prominent literary figures such as poet Yosano Akiko.
-
E.
Tokyo Shōken Torihikijo
Tokyo Shōken Torihikijo is the Japanese name for the Tokyo Stock Exchange, one of the world’s largest and most important securities markets.
- 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: Tokyo Shokonsha Triple: [Yasukuni Shrine, formerName, Tokyo Shokonsha]
Generated description
Tokyo Shokonsha was the original name of what is now Yasukuni Shrine, a Shinto shrine in Tokyo dedicated to commemorating Japan’s war dead.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tokyo Shokonsha Target entity description: Tokyo Shokonsha was the original name of what is now Yasukuni Shrine, a Shinto shrine in Tokyo dedicated to commemorating Japan’s war dead.
-
A.
Kodansha
Kodansha is a major Japanese publishing company best known for producing and distributing popular manga, novels, and magazines worldwide.
-
B.
Chūō Kōron Shinsha
Chūō Kōron Shinsha is a major Japanese publishing company known for its influential literary and cultural magazines and books.
-
C.
Shueisha
Shueisha is a major Japanese publishing company best known for producing popular manga magazines such as Weekly Shōnen Jump.
-
D.
Bunko-dō publishing house
Bunko-dō publishing house was a Japanese publisher known for its association with prominent literary figures such as poet Yosano Akiko.
-
E.
Tokyo Shōken Torihikijo
Tokyo Shōken Torihikijo is the Japanese name for the Tokyo Stock Exchange, one of the world’s largest and most important securities markets.
- 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_69d6ab67950c8190be08450a06228c4b |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91cb59ce4819099999b8755fb8b98 |
completed | April 10, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60ab3ae2481908f65d8ac61a6b2e4 |
completed | May 2, 2026, 2:31 p.m. |
| NEDg | Description generation | batch_69f60bdd8d508190813178ff4c77afcf |
completed | May 2, 2026, 2:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f60c67c680819087630d190d0a008f |
completed | May 2, 2026, 2:38 p.m. |
Created at: April 8, 2026, 9:51 p.m.