Triple
T19938332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanjo Ohashi |
E479234
|
entity |
| Predicate | romanization |
P2508
|
FINISHED |
| Object |
Sanjō Ōhashi
Sanjō Ōhashi is a historic bridge in Kyoto, Japan, traditionally regarded as the terminus of the Tōkaidō road and an important cultural landmark.
|
E1403317
|
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: Sanjō Ōhashi | Statement: [Sanjo Ohashi, romanization, Sanjō Ōhashi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sanjō Ōhashi Context triple: [Sanjo Ohashi, romanization, Sanjō Ōhashi]
-
A.
Wakamiya Ōji
Wakamiya Ōji is the main ceremonial avenue of Kamakura, Japan, leading from the waterfront through the city to Tsurugaoka Hachimangū Shrine.
-
B.
Katayama Tōkuma
Katayama Tōkuma was a prominent Meiji-era Japanese architect known for pioneering Western-style imperial and public buildings in Japan.
-
C.
Yasuji
Yasuji is a Japanese given name commonly used for males and borne by various notable figures in Japan.
-
D.
Yasutake
Yasutake is a Japanese surname associated with individuals of Japanese heritage, including the American nonprofit leader Irene Hirano.
-
E.
Hara Sankei
Hara Sankei was a Japanese businessman and art patron best known for creating and developing the historic Sankeien Garden in Yokohama.
- 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: Sanjō Ōhashi Triple: [Sanjo Ohashi, romanization, Sanjō Ōhashi]
Generated description
Sanjō Ōhashi is a historic bridge in Kyoto, Japan, traditionally regarded as the terminus of the Tōkaidō road and an important cultural landmark.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sanjō Ōhashi Target entity description: Sanjō Ōhashi is a historic bridge in Kyoto, Japan, traditionally regarded as the terminus of the Tōkaidō road and an important cultural landmark.
-
A.
Wakamiya Ōji
Wakamiya Ōji is the main ceremonial avenue of Kamakura, Japan, leading from the waterfront through the city to Tsurugaoka Hachimangū Shrine.
-
B.
Katayama Tōkuma
Katayama Tōkuma was a prominent Meiji-era Japanese architect known for pioneering Western-style imperial and public buildings in Japan.
-
C.
Yasuji
Yasuji is a Japanese given name commonly used for males and borne by various notable figures in Japan.
-
D.
Yasutake
Yasutake is a Japanese surname associated with individuals of Japanese heritage, including the American nonprofit leader Irene Hirano.
-
E.
Hara Sankei
Hara Sankei was a Japanese businessman and art patron best known for creating and developing the historic Sankeien Garden in Yokohama.
- 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_69d8e522a17c819095165d4d24939fd8 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65a190ac08190b9dc7955c9764a71 |
completed | April 20, 2026, 4:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07f6ec40f88190926f1330300fdc61 |
completed | May 16, 2026, 4:47 a.m. |
| NEDg | Description generation | batch_6a07f9c8f6c08190a949ebbb70b08d01 |
completed | May 16, 2026, 4:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07fb3a144c8190b9bf2148702d6b6c |
completed | May 16, 2026, 5:06 a.m. |
Created at: April 10, 2026, 1:53 p.m.