Triple
T11981310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of the Yalu River |
E285165
|
entity |
| Predicate | notableShip |
P3345
|
FINISHED |
| Object |
Matsushima
Matsushima was a Japanese protected cruiser that served as a flagship of the Imperial Japanese Navy during the First Sino-Japanese War.
|
E992031
|
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: Matsushima | Statement: [Battle of the Yalu River, notableShip, Matsushima]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matsushima Context triple: [Battle of the Yalu River, notableShip, Matsushima]
-
A.
Oiyama
Oiyama is the climactic final race of the Hakata Gion Yamakasa festival in Fukuoka, where teams dash through the streets carrying elaborately decorated floats.
-
B.
Yagiyama
Yagiyama is a hilly district in Sendai, Japan, known for its zoo, amusement park, and scenic views over the city.
-
C.
Sasayama
Sasayama is a historic castle town in Hyōgo Prefecture, Japan, known for its well-preserved Edo-period streets, Sasayama Castle ruins, and traditional local cuisine.
-
D.
Ōyama
Ōyama is a Japanese surname borne by various notable figures in Japan’s military, political, and cultural history.
-
E.
Fukuchiyama
Fukuchiyama is a regional city in northern Kyoto Prefecture, Japan, known as a historical castle town and commercial hub for the surrounding rural area.
- 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: Matsushima Triple: [Battle of the Yalu River, notableShip, Matsushima]
Generated description
Matsushima was a Japanese protected cruiser that served as a flagship of the Imperial Japanese Navy during the First Sino-Japanese War.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Matsushima Target entity description: Matsushima was a Japanese protected cruiser that served as a flagship of the Imperial Japanese Navy during the First Sino-Japanese War.
-
A.
Oiyama
Oiyama is the climactic final race of the Hakata Gion Yamakasa festival in Fukuoka, where teams dash through the streets carrying elaborately decorated floats.
-
B.
Yagiyama
Yagiyama is a hilly district in Sendai, Japan, known for its zoo, amusement park, and scenic views over the city.
-
C.
Sasayama
Sasayama is a historic castle town in Hyōgo Prefecture, Japan, known for its well-preserved Edo-period streets, Sasayama Castle ruins, and traditional local cuisine.
-
D.
Ōyama
Ōyama is a Japanese surname borne by various notable figures in Japan’s military, political, and cultural history.
-
E.
Fukuchiyama
Fukuchiyama is a regional city in northern Kyoto Prefecture, Japan, known as a historical castle town and commercial hub for the surrounding rural area.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d90395a8788190bfbb3506c29e3825 |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65e94b6008190ae19c245c4c62b5e |
completed | May 2, 2026, 8:29 p.m. |
| NEDg | Description generation | batch_69f65ffd45e48190883c5b524b7c5e41 |
completed | May 2, 2026, 8:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6608ec32c8190803c6f5677c300d6 |
completed | May 2, 2026, 8:37 p.m. |
Created at: April 8, 2026, 9:46 p.m.