Triple
T22453874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ikeda Terumasa |
E555061
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Terumasa
Terumasa is a masculine Japanese given name historically borne by notable samurai and daimyō.
|
E1537496
|
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: Terumasa | Statement: [Ikeda Terumasa, givenName, Terumasa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terumasa Context triple: [Ikeda Terumasa, givenName, Terumasa]
-
A.
Takuma Sato
Takuma Sato is a Japanese racing driver best known for his career in Formula One and as a multiple Indianapolis 500 winner in the IndyCar Series.
-
B.
Kazuki Nakajima
Kazuki Nakajima is a Japanese racing driver known for his Formula One stint with Williams and his multiple World Endurance Championship victories with Toyota, including wins at the 24 Hours of Le Mans.
-
C.
Masamichi Takano
Masamichi Takano is a cinematographer known for his work on the 2011 mixed martial arts drama film "Warrior."
-
D.
Masahiro Kobayashi
Masahiro Kobayashi is a Japanese actor best known for his role in the kaiju film "Godzilla, Mothra and King Ghidorah: Giant Monsters All-Out Attack."
-
E.
Ukyo Tachibana
Ukyo Tachibana is a popular, sickly yet graceful swordsman known for his swift Iaido-style techniques in the Samurai Shodown fighting game series.
- 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: Terumasa Triple: [Ikeda Terumasa, givenName, Terumasa]
Generated description
Terumasa is a masculine Japanese given name historically borne by notable samurai and daimyō.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Terumasa Target entity description: Terumasa is a masculine Japanese given name historically borne by notable samurai and daimyō.
-
A.
Takuma Sato
Takuma Sato is a Japanese racing driver best known for his career in Formula One and as a multiple Indianapolis 500 winner in the IndyCar Series.
-
B.
Kazuki Nakajima
Kazuki Nakajima is a Japanese racing driver known for his Formula One stint with Williams and his multiple World Endurance Championship victories with Toyota, including wins at the 24 Hours of Le Mans.
-
C.
Masamichi Takano
Masamichi Takano is a cinematographer known for his work on the 2011 mixed martial arts drama film "Warrior."
-
D.
Masahiro Kobayashi
Masahiro Kobayashi is a Japanese actor best known for his role in the kaiju film "Godzilla, Mothra and King Ghidorah: Giant Monsters All-Out Attack."
-
E.
Ukyo Tachibana
Ukyo Tachibana is a popular, sickly yet graceful swordsman known for his swift Iaido-style techniques in the Samurai Shodown fighting game series.
- 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b4d6368819082cafbbd83339fbf |
completed | April 29, 2026, 1:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b0c7d6324819086dc3b07bf77c64a |
completed | May 18, 2026, 12:56 p.m. |
| NEDg | Description generation | batch_6a0b0d2ba1e08190b2ebd1ee42641fd1 |
completed | May 18, 2026, 12:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b0daf9bac819086166985458f6742 |
completed | May 18, 2026, 1:01 p.m. |
Created at: April 16, 2026, 8:48 p.m.