Triple
T17825067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gamera vs. Guiron |
E445092
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object |
Miyuki Akiyama
Miyuki Akiyama is a Japanese actress best known for her role in the 1969 kaiju film "Gamera vs. Guiron."
|
E1454927
|
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: Miyuki Akiyama | Statement: [Gamera vs. Guiron, stars, Miyuki Akiyama]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Miyuki Akiyama Context triple: [Gamera vs. Guiron, stars, Miyuki Akiyama]
-
A.
Takako Yamada
Takako Yamada is a Japanese given name bearer, likely a woman known in Japan under the common female name "Takako."
-
B.
Takako Matsu
Takako Matsu is a Japanese actress and pop singer known for her prominent roles in film, television, and theater, as well as her successful music career.
-
C.
Takako Minekawa
Takako Minekawa is a Japanese musician and singer-songwriter known for her experimental pop and electronic music, often featuring playful, retro-futuristic sounds and themes.
-
D.
Takako Shirai
Takako Shirai is a Japanese singer-songwriter known for her work in pop and rock music since the late 1970s.
-
E.
Takako Yamazaki
Takako Yamazaki is a Japanese given name borne by various notable individuals in fields such as entertainment, sports, and the arts.
- 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: Miyuki Akiyama Triple: [Gamera vs. Guiron, stars, Miyuki Akiyama]
Generated description
Miyuki Akiyama is a Japanese actress best known for her role in the 1969 kaiju film "Gamera vs. Guiron."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Miyuki Akiyama Target entity description: Miyuki Akiyama is a Japanese actress best known for her role in the 1969 kaiju film "Gamera vs. Guiron."
-
A.
Takako Yamada
Takako Yamada is a Japanese given name bearer, likely a woman known in Japan under the common female name "Takako."
-
B.
Takako Matsu
Takako Matsu is a Japanese actress and pop singer known for her prominent roles in film, television, and theater, as well as her successful music career.
-
C.
Takako Minekawa
Takako Minekawa is a Japanese musician and singer-songwriter known for her experimental pop and electronic music, often featuring playful, retro-futuristic sounds and themes.
-
D.
Takako Shirai
Takako Shirai is a Japanese singer-songwriter known for her work in pop and rock music since the late 1970s.
-
E.
Takako Yamazaki
Takako Yamazaki is a Japanese given name borne by various notable individuals in fields such as entertainment, sports, and the arts.
- 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48914226c819083edcc78e00b2d42 |
completed | April 19, 2026, 7:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a091380428c8190b0535d3100e3c9a6 |
completed | May 17, 2026, 1:01 a.m. |
| NEDg | Description generation | batch_6a0914358a088190848fd658fa884cf1 |
completed | May 17, 2026, 1:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0914daf1188190bd8287ef06156c6f |
completed | May 17, 2026, 1:07 a.m. |
Created at: April 10, 2026, 10:15 a.m.