Triple
T15165475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perfume |
E362327
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Tokyo Girl
Tokyo Girl is a synth-pop single by the Japanese techno-pop trio Perfume, known for its futuristic sound and stylish, city-themed visuals.
|
E1141539
|
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 Girl | Statement: [Perfume, notableWork, Tokyo Girl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tokyo Girl Context triple: [Perfume, notableWork, Tokyo Girl]
-
A.
Harajuku Lovers
Harajuku Lovers is a Japanese street-style-inspired fashion and accessories brand created by musician and designer Gwen Stefani.
-
B.
The Tokyo Blues
The Tokyo Blues is a 1962 jazz album by pianist and composer Horace Silver that blends hard bop with Japanese musical influences.
-
C.
Tokyo Pop
Tokyo Pop is a 1988 romantic comedy-drama film about an aspiring American singer who travels to Japan and becomes involved in the local rock scene.
-
D.
Tokyo Road
"Tokyo Road" is a hard rock song by the American band Bon Jovi from their 1985 album "7800° Fahrenheit."
-
E.
Shinjuku Mylord
Shinjuku Mylord is a popular multi-story shopping and dining complex directly connected to Shinjuku Station in Tokyo, known for its fashion boutiques, restaurants, and easy access to surrounding commercial areas.
- 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 Girl Triple: [Perfume, notableWork, Tokyo Girl]
Generated description
Tokyo Girl is a synth-pop single by the Japanese techno-pop trio Perfume, known for its futuristic sound and stylish, city-themed visuals.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tokyo Girl Target entity description: Tokyo Girl is a synth-pop single by the Japanese techno-pop trio Perfume, known for its futuristic sound and stylish, city-themed visuals.
-
A.
Harajuku Lovers
Harajuku Lovers is a Japanese street-style-inspired fashion and accessories brand created by musician and designer Gwen Stefani.
-
B.
The Tokyo Blues
The Tokyo Blues is a 1962 jazz album by pianist and composer Horace Silver that blends hard bop with Japanese musical influences.
-
C.
Tokyo Pop
Tokyo Pop is a 1988 romantic comedy-drama film about an aspiring American singer who travels to Japan and becomes involved in the local rock scene.
-
D.
Tokyo Road
"Tokyo Road" is a hard rock song by the American band Bon Jovi from their 1985 album "7800° Fahrenheit."
-
E.
Shinjuku Mylord
Shinjuku Mylord is a popular multi-story shopping and dining complex directly connected to Shinjuku Station in Tokyo, known for its fashion boutiques, restaurants, and easy access to surrounding commercial areas.
- 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_69d85a087b7c81908baa94a53dac8d68 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0064c6244819085daf8e1eafdf3f2 |
completed | April 15, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fec887fbf08190b42dd25a99b7770d |
completed | May 9, 2026, 5:39 a.m. |
| NEDg | Description generation | batch_69fec974f39c819081dcec5c18090cf7 |
completed | May 9, 2026, 5:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69feca9d1a5c8190b0c649f83a74231b |
completed | May 9, 2026, 5:48 a.m. |
Created at: April 10, 2026, 3:08 a.m.